© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38445
    Prev
    Next
    INDEX
    Explanations

    you can

    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
    帮æĪij
    -0.09
    /help
    -0.09
    以人为
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.09
    adal
    -0.08
    幸
    -0.08
    _Execute
    -0.08
    indh
    -0.08
    izr
    -0.08
    æľįåĬ¡èĥ½åĬĽ
    -0.08
    POSITIVE LOGITS
    西æ´ĭ
    0.10
    æķ´å¤©
    0.10
    è½»æĺĵ
    0.09
    个æĢ§
    0.08
    ç©¿
    0.08
    å¾Ī容æĺĵ
    0.08
    åŃĺ
    0.08
    鬯
    0.08
    åıįå¤į
    0.08
    asily
    0.08
    Activations Density 0.035%

    No Known Activations