© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20028
    Prev
    Next
    INDEX
    Explanations

    GoSpotCheck phone app

    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
    uset
    -0.09
    jing
    -0.09
    æĻ¨
    -0.09
    atten
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    _INFORMATION
    -0.09
    æŁĵ
    -0.08
    cern
    -0.08
    碰æĴŀ
    -0.08
    å¾Ĺèµ·
    -0.08
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.11
    éĢłè¡Ģ
    0.10
    ä¸įå®Į
    0.09
     Inc
    0.09
    вели
    0.08
    è¿IJèIJ¥ç®¡çIJĨ
    0.08
    å¸Ĥåľºç«ŀäºī
    0.08
    achs
    0.08
    æ³ķåѦ
    0.08
    æĪĭ
    0.08
    Activations Density 0.064%

    No Known Activations