© 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. 23195
    Prev
    Next
    INDEX
    Explanations

    1st, 101, industry

    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
    京
    -0.08
    éĺ³åİ¿
    -0.08
    ACHE
    -0.08
    /pp
    -0.08
    ì¹´
    -0.08
    appointed
    -0.08
    Ä°Z
    -0.08
    è¸ıå®ŀ
    -0.08
    è¿ĻçĤ¹
    -0.08
    éĹŃ
    -0.08
    POSITIVE LOGITS
    äºĨä¸ĭæĿ¥
    0.08
    责任人
    0.08
    ä¸ĵåijĺ
    0.08
     Arn
    0.08
    楼å®ĩ
    0.08
    è´
    0.08
    çĶŁäº§å·¥èīº
    0.08
    èµ°åİ»
    0.08
    æĬ¬èµ·
    0.08
    æį¢æĿ¥
    0.08
    Activations Density 0.421%

    No Known Activations