© 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. 47921
    Prev
    Next
    INDEX
    Explanations

    high school class commitments

    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
    æ¯ĭ
    -0.10
    astle
    -0.10
     Sans
    -0.09
    _MR
    -0.09
    åľ¨èģĮ
    -0.09
    éĢIJ
    -0.08
    hart
    -0.08
    羯
    -0.08
    job
    -0.08
    éģ¥
    -0.08
    POSITIVE LOGITS
    é«ĺä¸ŃçĶŁ
    0.11
    æĹ©å°±
    0.10
    æŃĨ
    0.09
    ç±½
    0.09
    ç»®
    0.09
    åŁİå¸ĤçļĦ
    0.09
    é«ĺä¸Ń
    0.09
    åħ¨åĽ½åIJĦåľ°
    0.09
    çľģ份
    0.09
    è¿ĽåŁİ
    0.09
    Activations Density 0.146%

    No Known Activations