© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    university of california

    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
    oooooooo
    -0.10
    Nation
    -0.09
    jian
    -0.09
    éĿ©
    -0.09
    ä»ĸå¦Ī
    -0.09
    ify
    -0.09
    (strict
    -0.08
    éľĵ
    -0.08
    dan
    -0.08
    esti
    -0.08
    POSITIVE LOGITS
    ฯ
    0.10
    æĸ¼
    0.09
    ä¸įæĩĪ
    0.08
    åĮĹè·¯
    0.08
    æµ·å¤ĸ
    0.08
    andel
    0.08
    åĮ»åѦéĻ¢
    0.08
    -pres
    0.08
    æĢ»å·¥ä¼ļ
    0.08
     ÐŁÐµÑĤ
    0.08
    Activations Density 0.062%

    No Known Activations