© 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. 27708
    Prev
    Next
    INDEX
    Explanations

    between and

    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
    ç»Ļä½łä»¬
    -0.10
    ä¸İåħ¶ä»ĸ
    -0.09
    omap
    -0.09
    _BOUNDS
    -0.08
    .scala
    -0.08
    èĭ±æł¼
    -0.08
    鸷
    -0.08
    weis
    -0.08
    _SDK
    -0.08
    æ¯Ķéĩį
    -0.08
    POSITIVE LOGITS
    æĹ¢æľī
    0.10
    ä¹ĭéĹ´
    0.10
    è¿ĻåĿĹ
    0.09
    ä¹ĭéĸĵ
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.09
    standing
    0.09
    åıªèĥ½è¯´
    0.09
    ä¹ĭéĹ´çļĦ
    0.09
    è¿Ļè¾¹
    0.09
    éĹ´çļĦ
    0.08
    Activations Density 0.257%

    No Known Activations