© 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. 7-RESID-POST-AA
    11. 6635
    Prev
    Next
    INDEX
    Explanations

    win

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CoreApplication
    -0.07
    .mipmap
    -0.07
     steadily
    -0.07
    (note
    -0.07
    dac
    -0.06
     sore
    -0.06
     وأشار
    -0.06
    irim
    -0.06
    _iface
    -0.06
    iscrimination
    -0.06
    POSITIVE LOGITS
     Exhib
    0.07
    呈现
    0.07
    김
    0.07
    /jav
    0.07
    英超
    0.07
    .removeListener
    0.07
    }\.[
    0.07
    ᛂ
    0.06
                              ↵
    0.06
    FML
    0.06
    Activations Density 0.018%

    No Known Activations