© 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. 62397
    Prev
    Next
    INDEX
    Explanations

    separators or list introducers

    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
    ç»Ŀ
    -0.10
    è¯Ńæ°Ķ
    -0.10
    æ»ŀ
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    亲
    -0.09
    網åıĭ
    -0.09
    [mid
    -0.09
    éĤ£ä»½
    -0.09
    glyphicon
    -0.09
    åħ¶æ¬¡
    -0.09
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.08
    _si
    0.08
    Ñģи
    0.08
    伦
    0.08
    å½ĵ
    0.08
    à¸ģารà¸Ĺำ
    0.08
     DAM
    0.08
    ì±ħ
    0.08
    /op
    0.07
    ä¸Ģ个人
    0.07
    Activations Density 0.195%

    No Known Activations