© 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. 113766
    Prev
    Next
    INDEX
    Explanations

    questions involving numbers

    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
    经验
    -0.08
     الخي
    -0.07
    ikit
    -0.07
     difficulties
    -0.07
    ཁ
    -0.07
    (dict
    -0.07
    IALIZED
    -0.07
    ࡔ
    -0.07
     buddies
    -0.07
     static
    -0.07
    POSITIVE LOGITS
    -muted
    0.08
    -em
    0.08
     ebx
    0.07
     traf
    0.07
     TRAN
    0.07
     Brut
    0.07
    𝑬
    0.07
     Cream
    0.07
    _ref
    0.07
     Lat
    0.07
    Activations Density 0.117%

    No Known Activations