© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9786
    Prev
    Next
    INDEX
    Explanations

    parentheses and hyphens

    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
    éĢĢè´§
    -0.09
    ä»ĸçŁ¥éģĵ
    -0.09
    å¤ĸæı´
    -0.09
    éĻ¢éĻ¢éķ¿
    -0.08
    éĻįä½İæĪIJæľ¬
    -0.08
     circum
    -0.08
    èĹı
    -0.08
    å¦Ĥæŀľä½łæĥ³
    -0.08
    å°ıé¢Ŀ
    -0.08
    (border
    -0.08
    POSITIVE LOGITS
    级以ä¸Ĭ
    0.09
    ittel
    0.08
    æ»Ł
    0.08
    éħįæľī
    0.08
    çŀ©
    0.08
    ingen
    0.08
    æĬľ
    0.08
     наÑģел
    0.08
    à¹Ģà¸Ī
    0.08
    èĢ½
    0.08
    Activations Density 0.026%

    No Known Activations