© 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. 6433
    Prev
    Next
    INDEX
    Explanations

    finger injuries

    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
    çļĦé£Łçī©
    -0.09
     Burst
    -0.09
     abandonment
    -0.09
     Leak
    -0.08
    ussen
    -0.08
    临
    -0.08
    .EVT
    -0.08
    ë³Ħ
    -0.08
    æ¼ıæ°´
    -0.08
    媾
    -0.08
    POSITIVE LOGITS
    å¨ģ
    0.13
    å¨ģåĬĽ
    0.10
    dre
    0.09
    ÑĢабоÑĤаÑĤÑĮ
    0.09
    æ¯ķ
    0.09
    é«ĺåİĭ
    0.09
    强大çļĦ
    0.09
     ÑĢабоÑĤа
    0.09
    æ¾İæ¹ĥ
    0.09
    éĥ¨ä»¶
    0.08
    Activations Density 0.102%

    No Known Activations