© 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. 58423
    Prev
    Next
    INDEX
    Explanations

    favor or against

    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«ĸ
    -0.09
    itzer
    -0.09
    åı£æ°´
    -0.09
    па
    -0.08
    为èĩªå·±
    -0.08
    çļĦèī¯å¥½
    -0.08
    ä¸ĬåįĬå¹´
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    idores
    -0.08
    нÑĮ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.13
    emon
    0.10
    é¡¿
    0.10
    éĤ£ä½į
    0.10
    è¿Ļè¾¹
    0.10
    PELL
    0.10
    éĢ¸
    0.10
    éĤ£äºĽ
    0.09
     ÄijÆ°Æ¡ng
    0.09
    ONY
    0.09
    Activations Density 0.038%

    No Known Activations