© 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. 1864
    Prev
    Next
    INDEX
    Explanations

    their respective

    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
    .Unicode
    -0.09
    ç¿
    -0.09
    串
    -0.09
    æī¿æĭħ
    -0.09
    人群ä¸Ń
    -0.09
    æī¿æĭħ责任
    -0.09
    çĽ²
    -0.09
    æĹģ
    -0.09
    é£İæīĩ
    -0.09
    SYM
    -0.08
    POSITIVE LOGITS
     respective
    0.09
    uent
    0.09
    èĩªåĪ¶
    0.08
    lov
    0.08
    ä¸ĩæĪ·
    0.08
    涮
    0.08
    槿
    0.08
    uit
    0.08
    subs
    0.08
    uer
    0.08
    Activations Density 0.003%

    No Known Activations