© 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. 71006
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Hol
    -0.09
     phúc
    -0.08
    _super
    -0.07
    流行的
    -0.07
    下手
    -0.07
    내
    -0.06
    _uuid
    -0.06
     nick
    -0.06
    粟
    -0.06
    泽
    -0.06
    POSITIVE LOGITS
    等症状
    0.07
    (AdapterView
    0.07
    emas
    0.06
     الاجتماعية
    0.06
    .showMessage
    0.06
     coment
    0.06
     intense
    0.06
    blems
    0.06
    水墨
    0.06
     Somehow
    0.06
    Activations Density 0.063%

    No Known Activations