© 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. 59272
    Prev
    Next
    INDEX
    Explanations

    roles

    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
    üh
    -0.08
    蹩
    -0.07
    西亚
    -0.07
     crimes
    -0.07
    isOk
    -0.07
    ﹰ
    -0.07
    �
    -0.07
    .pres
    -0.07
    imbabwe
    -0.07
     cheeses
    -0.07
    POSITIVE LOGITS
    stellar
    0.07
    .Kind
    0.07
    鲞
    0.07
     Termin
    0.07
    �
    0.07
    	random
    0.07
    .ViewModels
    0.07
     większość
    0.07
     chosen
    0.07
    你会发现
    0.06
    Activations Density 0.009%

    No Known Activations