© 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. 7-RESID-POST-AA
    11. 42026
    Prev
    Next
    INDEX
    Explanations

    ssh

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANCED
    -0.07
    (fun
    -0.07
    电子
    -0.07
    тир
    -0.07
     elast
    -0.07
     DARK
    -0.07
    郜
    -0.07
    Ȁ
    -0.07
    ﮥ
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    第一个
    0.07
    .stem
    0.07
     mell
    0.07
     odds
    0.06
     merupakan
    0.06
    .jackson
    0.06
     PHONE
    0.06
    所有人都
    0.06
     schizophrenia
    0.06
    means
    0.06
    Activations Density 0.004%

    No Known Activations