© 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. 5502
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    ãģ¨ãģĵãĤįãģ§
    -0.10
    ðŁı»
    -0.10
    éĢµ
    -0.10
    人éĥ½
    -0.09
     ÑģобÑģÑĤвенно
    -0.09
    ä¹IJ趣
    -0.09
    ÅĦ
    -0.09
    à°³
    -0.09
    ë¡Ń
    -0.09
    ä¼ļå±ķ
    -0.09
    POSITIVE LOGITS
    ãģĦãģ¾ãģĻ
    0.10
    ingly
    0.10
    orrect
    0.08
    ième
    0.08
    ÙĴ
    0.08
    ras
    0.08
    à¹Į
    0.08
    оÑī
    0.08
    ry
    0.08
    mar
    0.08
    Activations Density 0.060%

    No Known Activations