© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    good, great, or excellent descriptions

    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
    ç½²
    -0.08
    æĹ¶ä»£çļĦ
    -0.08
    èĥ½ä¸įèĥ½
    -0.08
    èIJ½åĪ°å®ŀå¤Ħ
    -0.08
    uku
    -0.08
     lá»ĩ
    -0.08
    宣è¨Ģ
    -0.08
    éĢ¡
    -0.08
    ç¦Ħ
    -0.08
    éĻIJéĩı
    -0.08
    POSITIVE LOGITS
    æĹłæ¯Ķ
    0.10
    ibraries
    0.10
    unts
    0.10
     Pai
    0.10
    benh
    0.10
    ernes
    0.09
    éĿŀ常好çļĦ
    0.09
    eling
    0.09
    èİ«è¿ĩäºİ
    0.09
    목
    0.09
    Activations Density 0.062%

    No Known Activations