© 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. 18017
    Prev
    Next
    INDEX
    Explanations

    help, prevent, unavoidable

    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
    毫ä¸įçĬ¹è±«
    -0.10
    侯
    -0.09
    ç¥Ī祷
    -0.09
    atura
    -0.09
    毫ä¸į
    -0.08
    å¦ĩ
    -0.08
     Lives
    -0.08
    ucs
    -0.08
     KEEP
    -0.08
    士
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.11
    æĪIJ为ä¸Ģ个
    0.10
    没æ³ķ
    0.09
    èĺĸ
    0.09
    amental
    0.09
    屦
    0.09
    æ·±åĪĩ
    0.09
    嵩
    0.09
    éĥ½è§īå¾Ĺ
    0.09
    è¦ģ害
    0.09
    Activations Density 0.037%

    No Known Activations