© 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. 3992
    Prev
    Next
    INDEX
    Explanations

    predicting consequences

    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
    æİĮæı¡
    -0.09
    åģıå·®
    -0.08
    主è§Ĥ
    -0.08
    /operator
    -0.08
    çł´ç¢İ
    -0.08
    ä¸įçĶĺ
    -0.08
    clipse
    -0.08
    .rad
    -0.08
    èĻ
    -0.08
    èįIJ
    -0.08
    POSITIVE LOGITS
     Burton
    0.10
     cane
    0.09
    ä¹į
    0.09
    ä¸Ńåħ³
    0.09
    诱åıij
    0.09
    ilig
    0.08
    çİĩé¢Ĩ
    0.08
    æ¯ıä¸Ģ个人
    0.08
    ç½®æį¢
    0.08
    大æĪĺ
    0.08
    Activations Density 0.074%

    No Known Activations