© 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 EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 109446
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens — digits, numbers and year-like numerals in the text.

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     заявк
    -0.07
    инд
    -0.06
    Western
    -0.06
     Phill
    -0.06
    HSV
    -0.06
    Петербур
    -0.06
     güvenlik
    -0.06
     handjob
    -0.06
    .toolStrip
    -0.06
     스
    -0.06
    POSITIVE LOGITS
     guarda
    0.09
     headlines
    0.08
    _home
    0.08
    说完
    0.08
     tend
    0.07
    anger
    0.07
    见过
    0.07
    开口
    0.07
    呈现
    0.07
    מתי
    0.07
    Activations Density 0.783%

    No Known Activations