© 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. 63216
    Prev
    Next
    INDEX
    Explanations

    forum and community boards

    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
    çĸij
    -0.11
    ãĤ¾
    -0.09
    æĪij以为
    -0.09
    è¾Ľ
    -0.08
    iterals
    -0.08
    ä¸ĢåľĪ
    -0.08
    ool
    -0.08
    ç»Ļèĩªå·±
    -0.08
    _PACKAGE
    -0.08
    äs
    -0.08
    POSITIVE LOGITS
    主åĬĽ
    0.09
    erts
    0.08
    çİĭçīĮ
    0.08
    çĶ·ä¸»è§Ĵ
    0.08
     Dew
    0.08
    ä¸įæĸŃå¢ŀåĬł
    0.08
    çĶ·åŃ©
    0.08
    iances
    0.08
     offerings
    0.08
    åıĭæĥħéĵ¾æİ¥
    0.08
    Activations Density 0.165%

    No Known Activations