© 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. 53597
    Prev
    Next
    INDEX
    Explanations

    button or link

    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
    èĬĴ
    -0.10
    æ®ļ
    -0.09
    弥补
    -0.09
    ified
    -0.09
     Bend
    -0.09
    iquement
    -0.09
    é£İæł¼
    -0.08
    antry
    -0.08
    ä¸įèĪį
    -0.08
    ç§ķ
    -0.08
    POSITIVE LOGITS
     button
    0.11
    Retry
    0.10
    stoff
    0.09
    æĮīéĴ®
    0.09
    è¿IJ转
    0.09
    button
    0.09
    emark
    0.08
    åŃĹæł·
    0.08
    /ref
    0.08
    ä¹ĭç±»çļĦ
    0.08
    Activations Density 0.101%

    No Known Activations