© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32010
    Prev
    Next
    INDEX
    Explanations

    DO NOT ALTER OR REMOVE COPYRIGHT

    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
    _exc
    -0.09
    æĬļæij¸
    -0.09
    çĭİ
    -0.08
    ä¸Ńä¿¡
    -0.08
    åĩ¡
    -0.08
    èĥ¥
    -0.08
    å¼ı
    -0.08
    çĤŃ
    -0.08
    åįģéĩĮ
    -0.08
    躬
    -0.08
    POSITIVE LOGITS
    æľĿ
    0.09
    tee
    0.09
    ä¸ĢåIJij
    0.09
    ç¼Ĩ
    0.09
    éģĹæ¼ı
    0.09
    ä¸Ģè´¯
    0.09
    amo
    0.08
    à¸ģระà¸Ĺ
    0.08
    糧
    0.08
    ãĤĴåıĸãĤĬ
    0.08
    Activations Density 0.089%

    No Known Activations