© 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. 39882
    Prev
    Next
    INDEX
    Explanations

    locations or venues

    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
    åĮł
    -0.10
    ä¸ĸçķĮ级
    -0.09
     Livingston
    -0.09
    acro
    -0.09
    çļĦ人æĿ¥è¯´
    -0.09
    åĿŃ
    -0.09
    енÑĮ
    -0.08
    _OD
    -0.08
    ä¸ĵ家
    -0.08
    æ§Ľ
    -0.08
    POSITIVE LOGITS
     schools
    0.15
    åŃ¦æł¡
    0.14
     school
    0.14
    æł¡åĽŃ
    0.14
    åŃ¦æł¡çļĦ
    0.13
    é«ĺæł¡
    0.12
     Schools
    0.12
    é»ī
    0.11
    åľ¨åŃ¦æł¡
    0.11
    schools
    0.11
    Activations Density 0.134%

    No Known Activations