© 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. 17744
    Prev
    Next
    INDEX
    Explanations

    However,

    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
    æīĢ以æĪij
    -0.11
     thus
    -0.11
    æĸ¼æĺ¯
    -0.11
    常å§Ķ
    -0.10
    äºİæĺ¯
    -0.10
    æł·çļĦ
    -0.10
     zwar
    -0.10
     therefore
    -0.10
    owed
    -0.09
    åijµæĬ¤
    -0.09
    POSITIVE LOGITS
    że
    0.11
    oft
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    umber
    0.09
    ä¸İæѤåIJĮæŶ
    0.09
    _MALLOC
    0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    0.08
    纵è§Ĥ
    0.08
    essian
    0.08
    åľ¨æĪij
    0.08
    Activations Density 0.070%

    No Known Activations