© 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. 55059
    Prev
    Next
    INDEX
    Explanations

    ammunition types

    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
    ç¾İ好çļĦ
    -0.11
    ä¸ĥ大
    -0.10
    æ¡Į
    -0.10
    brew
    -0.10
     Brewer
    -0.09
    ç¿ĺ
    -0.09
    å§Ŀ
    -0.09
    æ´ŀ
    -0.09
    饮éħĴ
    -0.09
    ç¾İ好
    -0.09
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.11
     shells
    0.09
    ctest
    0.09
    IRD
    0.09
    è¿Ļ家åħ¬åı¸
    0.09
    å¿ĥçĸ¼
    0.08
    landing
    0.08
    _plain
    0.08
    å·¡å¯Ł
    0.08
     landing
    0.08
    Activations Density 0.059%

    No Known Activations