© 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. 63348
    Prev
    Next
    INDEX
    Explanations

    NFL team names

    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
    æĹ©å°±
    -0.10
    ç»®
    -0.10
    åĩºåĽ½çķĻåѦ
    -0.10
    æł¹æľ¬ä¸į
    -0.09
    åŁºå»º
    -0.09
    æĺ¯åĽ½åĨħ
    -0.09
    EIF
    -0.09
    acent
    -0.09
    建设
    -0.08
    èŃ½
    -0.08
    POSITIVE LOGITS
    端æŃ£
    0.10
    éĢIJ
    0.09
    APS
    0.09
    æ¯ĭ
    0.09
    tip
    0.09
     наÑĤÑĥÑĢалÑĮн
    0.09
    job
    0.09
     tiêu
    0.09
     بÙĪ
    0.09
    تÙĨ
    0.09
    Activations Density 0.140%

    No Known Activations