© 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. 34313
    Prev
    Next
    INDEX
    Explanations

    fungal, fungi, mold

    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
    满
    -0.10
    æ±īåł¡
    -0.09
    ç¾ļ
    -0.09
    odont
    -0.09
    chrome
    -0.08
     Chicken
    -0.08
    istar
    -0.08
    丰å¯Į
    -0.08
    åįıåIJĮ
    -0.08
     AIDS
    -0.08
    POSITIVE LOGITS
    潮湿
    0.14
    éľī
    0.13
    湿度
    0.11
    ðŁįĦ
    0.10
    æ¹ľ
    0.10
    åĽłåľ°
    0.09
    undi
    0.09
    +-+-
    0.09
    è´Ńçī©
    0.09
    éĢĤæŶ
    0.09
    Activations Density 0.104%

    No Known Activations