© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 72009
    Prev
    Next
    INDEX
    Explanations

    affiliates

    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
    Negative Logits
    "#
    -0.07
    ",↵
    -0.07
     sadness
    -0.07
     did
    -0.07
    𫄷
    -0.06
    发光
    -0.06
     estimating
    -0.06
     cổ
    -0.06
    ступил
    -0.06
     строки
    -0.06
    POSITIVE LOGITS
    datagrid
    0.08
     Number
    0.07
    הג
    0.07
     okre
    0.07
    水
    0.07
    ivan
    0.07
    CONT
    0.06
     maint
    0.06
    OCUS
    0.06
     Milf
    0.06
    Activations Density 0.010%

    No Known Activations