© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8706
    Prev
    Next
    INDEX
    Explanations

    equations and assignments

    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
    å¾ħéģĩ
    -0.09
    å°±åĥıæĺ¯
    -0.09
    å°±åĥı
    -0.09
    elves
    -0.09
    å¿ħå°Ĩ
    -0.09
    æĿ¥è¯´
    -0.09
    çļĦå¿ĥ
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    ä¸Ģå®ļæĺ¯
    -0.09
    ä¸ĢèĪ¬æĺ¯
    -0.09
    POSITIVE LOGITS
    /is
    0.19
    /=
    0.14
    *=*=
    0.13
     ë¬¼ë¡ł
    0.11
    ãģ£ãģįãĤĬ
    0.10
    ==============↵
    0.10
    ities
    0.10
    éĤ£ç§į
    0.10
    /w
    0.10
    ===========
    0.10
    Activations Density 0.704%

    No Known Activations