© 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. 57159
    Prev
    Next
    INDEX
    Explanations

    some

    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
     Scotia
    -0.08
     Montana
    -0.07
     كذلك
    -0.07
    山西
    -0.07
    ель
    -0.07
    各个环节
    -0.07
    zt
    -0.07
    blood
    -0.07
     Miscellaneous
    -0.07
     Jefferson
    -0.07
    POSITIVE LOGITS
     auctions
    0.07
     nak
    0.07
    נד
    0.07
     mailed
    0.07
    手艺
    0.07
     forks
    0.07
    ítulo
    0.06
    /gr
    0.06
    فن
    0.06
    [method
    0.06
    Activations Density 0.025%

    No Known Activations