© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 30454
    Prev
    Next
    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that contain non‑ASCII/accented characters (letters with diacritics), i.e., foreign words and names.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vida
    -0.08
     Federal
    -0.08
     фут
    -0.07
    코
    -0.07
    அ
    -0.07
    oop
    -0.07
    uos
    -0.07
    .Unlock
    -0.07
     something
    -0.07
     perfectly
    -0.06
    POSITIVE LOGITS
    (training
    0.07
    死者
    0.07
    此案
    0.07
    Remaining
    0.07
     Instantiate
    0.07
    تط
    0.06
    .minutes
    0.06
     useClass
    0.06
    各项工作
    0.06
     счит
    0.06
    Activations Density 1.031%

    No Known Activations