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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 89242
    Prev
    Next
    INDEX
    Explanations

    /LICENSE

    np_max-act · gemini-2.0-flash
    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
    shaw
    -0.07
     dvd
    -0.07
    rtc
    -0.07
    挎
    -0.07
    vertisement
    -0.07
    咨询
    -0.07
    jc
    -0.07
    titulo
    -0.07
    WithEmailAndPassword
    -0.07
    хи
    -0.06
    POSITIVE LOGITS
    เผยแพร
    0.07
     celebr
    0.07
    流产
    0.07
    与众不同
    0.07
    �
    0.07
     gönder
    0.07
     Oliv
    0.07
    Objective
    0.07
    続きを
    0.07
     Seah
    0.07
    Activations Density 0.001%

    No Known Activations