© 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. 38580
    Prev
    Next
    INDEX
    Explanations

    focusing on implications and scope

    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
    éĢĽ
    -0.10
    ä¸ĢéĹ´
    -0.09
    æµ·æ£ł
    -0.09
    ç¼İ
    -0.08
    饮
    -0.08
    .consumer
    -0.08
    窥
    -0.08
    VD
    -0.08
    åľ°æ¯¯
    -0.08
     Consumer
    -0.08
    POSITIVE LOGITS
    ystack
    0.10
    è°ĭåĪĴ
    0.09
    请çĤ¹åĩ»
    0.09
    俾
    0.09
    è·Ĩ
    0.08
    侪
    0.08
    æ§Ĭ
    0.08
    fell
    0.08
     Feather
    0.08
    à¹īม
    0.08
    Activations Density 0.363%

    No Known Activations