© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    away alive

    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
    åĦĨ
    -0.10
    à¸ķà¸ģ
    -0.09
    æīĵåĩ»
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    ä¼İ
    -0.09
    åĻ¨æĿIJ
    -0.09
    è²Ķ
    -0.09
    æīĵåİĭ
    -0.09
    èį»
    -0.09
    iguous
    -0.09
    POSITIVE LOGITS
    åĩłåı¥
    0.10
    omas
    0.10
    é«ĺä½į
    0.09
    躬
    0.09
    ow
    0.08
    al
    0.08
    è¿Ļåı¥è¯Ŀ
    0.08
    æĨ©
    0.08
    yc
    0.08
    èĥ¥
    0.08
    Activations Density 0.007%

    No Known Activations