© 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. 4465
    Prev
    Next
    INDEX
    Explanations

    time and elapsed duration

    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
    éķ·æľŁ
    -0.10
    éķ¿æľŁ
    -0.09
     Redistributions
    -0.09
    맥
    -0.09
    /GL
    -0.09
     Pompe
    -0.08
    çŁŃæľŁ
    -0.08
    æīĵãģ¡
    -0.08
    çĿģå¼Ģ
    -0.08
    à¸Ĺà¸Ńà¸ĩ
    -0.08
    POSITIVE LOGITS
    æĪIJ绩
    0.15
    çļĦæĪIJ绩
    0.13
    éĢŁåº¦
    0.12
    æľĢå¿«çļĦ
    0.11
    çļĦæŶéĹ´
    0.11
    ä¸ļ绩
    0.10
    æŶéĹ´ä¸º
    0.10
     fastest
    0.10
    åĩºèī²
    0.10
    éĢŁåº¦å¿«
    0.10
    Activations Density 0.067%

    No Known Activations