© 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. 30917
    Prev
    Next
    INDEX
    Explanations

    Evil Dead Red Ale

    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
    è¹Ń
    -0.10
    åįĹéĥ¨
    -0.10
    arith
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    erman
    -0.08
    æ¿ij
    -0.08
    æĪijåı¯ä»¥
    -0.08
    è¿¢
    -0.08
     victorious
    -0.08
    桶
    -0.08
    POSITIVE LOGITS
    çѵ
    0.09
    OrFail
    0.09
    æŃ»èĢħ
    0.08
    æĿ
    0.08
    ispers
    0.08
    èĤĮ
    0.08
    æŃ¤äºº
    0.08
    æ¸Ń
    0.08
    ä¸İåIJ¦
    0.08
    å®īå±ħ
    0.08
    Activations Density 0.001%

    No Known Activations