© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63878
    Prev
    Next
    INDEX
    Explanations

    dates and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mania
    -0.10
    izu
    -0.10
    endale
    -0.10
    第ä¸ĢæŃ¥
    -0.09
    Ñıз
    -0.08
    åħ¨å¹´
    -0.08
    å¤ĸåªĴ
    -0.08
    licative
    -0.08
    _unused
    -0.08
     backpage
    -0.08
    POSITIVE LOGITS
    ä¿®æŃ£
    0.12
    oref
    0.11
    æĽ´æĸ°
    0.10
    .ht
    0.10
    è·Łä¸įä¸Ĭ
    0.09
     update
    0.09
    èĥ¥
    0.08
    è£ĺ
    0.08
    update
    0.08
    Update
    0.08
    Activations Density 0.094%

    No Known Activations