© 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. 56174
    Prev
    Next
    INDEX
    Explanations

    related items grouped together

    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
    æĵį
    -0.09
    åĶ¯
    -0.09
    大楼
    -0.08
    /high
    -0.08
    GetPosition
    -0.08
    ukt
    -0.08
    ä¸įä¸ĭ
    -0.08
    unal
    -0.08
    身影
    -0.08
    æĻĴ
    -0.07
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.12
     ÑģвÑıзан
    0.12
    ä½ľä¸ºä¸Ģ个
    0.12
    åħ·æľīä¸Ģå®ļ
    0.11
    æľīä¸Ģå®ļ
    0.10
    ç³»åĪĹ
    0.10
    åIJĮä¸Ģ个
    0.10
     Fet
    0.10
    ä¸Ģ群人
    0.10
    ä¸Ģ群
    0.10
    Activations Density 0.111%

    No Known Activations