© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 16372
    Prev
    Next
    INDEX
    Explanations

    bad language filtering

    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
    CHANGE
    -0.07
     interfer
    -0.07
    收敛
    -0.07
     til
    -0.07
     unintended
    -0.07
    amber
    -0.06
     parece
    -0.06
     concept
    -0.06
    -produced
    -0.06
    OnChange
    -0.06
    POSITIVE LOGITS
     łazien
    0.08
    蹼
    0.07
     Decl
    0.07
    .Dial
    0.07
    \Exception
    0.07
    评分
    0.07
     drib
    0.07
     Pont
    0.07
     Pistol
    0.07
    ,args
    0.07
    Activations Density 0.016%

    No Known Activations