© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 31187
    Prev
    Next
    INDEX
    Explanations

    found myself

    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
    ä»ĸ们çļĦ
    -0.09
    æ°¸è¿ľ
    -0.09
    æ°¸éģł
    -0.09
    ä»ĸ们
    -0.08
    è®®äºĭ
    -0.08
    åħ¶æīĢ
    -0.08
    åIJ¬è¯´
    -0.08
    åı¯ä»¥æł¹æį®
    -0.08
    abra
    -0.08
    ä¸Ĭä¼ł
    -0.08
    POSITIVE LOGITS
    åıijçݰèĩªå·±
    0.12
    ç»Ļèĩªå·±
    0.12
    æĦŁè§īèĩªå·±
    0.11
    å¸ĮæľĽèĩªå·±
    0.10
    ä½ĵä¼ļ
    0.10
    对èĩªå·±çļĦ
    0.10
    让èĩªå·±
    0.10
    æĪijèĩªå·±
    0.10
    ä½ĵéªĮ
    0.10
    feel
    0.10
    Activations Density 0.143%

    No Known Activations