© 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. 113675
    Prev
    Next
    INDEX
    Explanations

    Testing client

    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
    .withOpacity
    -0.07
    Soup
    -0.07
     Lam
    -0.07
     Lap
    -0.07
    -org
    -0.07
    仿佛
    -0.06
    徇
    -0.06
    OLLOW
    -0.06
     crossing
    -0.06
     accompagn
    -0.06
    POSITIVE LOGITS
    _DETAIL
    0.07
    =float
    0.07
    buckets
    0.07
     regress
    0.07
    -wheel
    0.07
     sleeps
    0.07
    _thread
    0.07
    [state
    0.07
    _reduce
    0.06
    	short
    0.06
    Activations Density 0.042%

    No Known Activations