© 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. 48567
    Prev
    Next
    INDEX
    Explanations

    offer to send

    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
    orts
    -0.12
    ä¸įè¦ģ太
    -0.10
    æ»ı
    -0.10
    Hints
    -0.09
    /win
    -0.09
    çĽ¸ä¼ł
    -0.09
    OLT
    -0.08
    Steam
    -0.08
    顺åĬ¿
    -0.08
    iras
    -0.08
    POSITIVE LOGITS
    ãģ£ãģ¦ãģıãĤĮ
    0.10
    ãģ¦ãģıãĤĮãģŁ
    0.10
    èµIJ
    0.10
    主åĬ¨
    0.09
    ä¸ĵéĹ¨ä¸º
    0.09
    åħ³å¿ĥ
    0.09
    帮æĪij
    0.09
    åľ¨æĪij
    0.09
    æ¾Ħæ¸ħ
    0.09
    æĥ¦
    0.09
    Activations Density 0.037%

    No Known Activations