© 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. 11516
    Prev
    Next
    INDEX
    Explanations

    level of

    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
    æĸ¹éĿ¢
    -0.10
    让æ¶Īè´¹èĢħ
    -0.09
    欲
    -0.09
    ä¸įæĩĪ
    -0.08
    ân
    -0.08
    ãĥ¡ãĥ³
    -0.08
    å°½éĩı
    -0.08
    ä¸ĢæŶ
    -0.08
    ston
    -0.07
     MISS
    -0.07
    POSITIVE LOGITS
    æ°´åĩĨ
    0.11
    æĬĢæľ¯æ°´å¹³
    0.10
    æľįåĬ¡æ°´å¹³
    0.09
     detail
    0.09
    ç¥ĸ
    0.09
    æı¡
    0.09
     gorge
    0.09
    /detail
    0.09
    detail
    0.09
    åĨ²åĩ»
    0.09
    Activations Density 0.049%

    No Known Activations