© 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. 11-RESID-POST-AA
    11. 128964
    Prev
    Next
    INDEX
    Explanations

    Train/metro stations

    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_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
    Keeping
    -0.07
     áo
    -0.07
     Shut
    -0.07
    옴
    -0.07
    気持ち
    -0.07
    谛
    -0.07
     Rooney
    -0.07
    ⁾
    -0.07
    潺
    -0.06
     Dos
    -0.06
    POSITIVE LOGITS
    ライフ
    0.07
     רוצים
    0.07
    uristic
    0.07
    .observable
    0.06
    временно
    0.06
    uetype
    0.06
    蒌
    0.06
     disappearing
    0.06
    --------↵
    0.06
    THREAD
    0.06
    Activations Density 0.005%

    No Known Activations