© 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. 56239
    Prev
    Next
    INDEX
    Explanations

    quantities and counts

    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¯ıä¸Ģä½į
    -0.10
    _layers
    -0.09
    æ¯ı个人
    -0.09
    ers
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    éĩijèŀįæľįåĬ¡
    -0.08
    å±Ĥå±Ĥ
    -0.08
    æŃ¥æŃ¥
    -0.08
     <<↵
    -0.08
    <decltype
    -0.08
    POSITIVE LOGITS
    被æįķ
    0.11
    å¤ļ家
    0.11
    諸
    0.10
    æĮ¨
    0.09
    åīįçŀ»
    0.09
    被åĪĹåħ¥
    0.09
    å¥Ĺ
    0.09
    åĮħæĭ¬
    0.09
    veral
    0.09
    诸
    0.09
    Activations Density 0.373%

    No Known Activations