© 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. 59162
    Prev
    Next
    INDEX
    Explanations

    font families

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éģ¿
    -0.10
    å·¡
    -0.09
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.09
     Pell
    -0.09
    æݪ
    -0.09
    éĵº
    -0.09
     poil
    -0.09
    éĭª
    -0.08
    èµ°ä¸ĭåİ»
    -0.08
    æĬĵç´§
    -0.08
    POSITIVE LOGITS
    åĽłæŀľ
    0.10
    楷
    0.09
    _closure
    0.09
    竺
    0.08
    iet
    0.08
    (selection
    0.08
    iges
    0.08
    åģ¶çĦ¶
    0.08
    ofil
    0.08
    .getResult
    0.08
    Activations Density 0.061%

    No Known Activations