© 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. 36221
    Prev
    Next
    INDEX
    Explanations

    giving new life

    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
    èĢĥ
    -0.09
    è¶Ĭ
    -0.08
    VAS
    -0.08
    ä¸įè¡Į
    -0.08
    .Ignore
    -0.07
    rev
    -0.07
    SystemService
    -0.07
    åĤ»
    -0.07
    æĭ¿æĿ¥
    -0.07
    .parents
    -0.07
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.10
    éĻ¡
    0.10
    éŀį
    0.10
    uyến
    0.09
    è¿Ļæĸ¹éĿ¢
    0.09
    ç¢Ľ
    0.09
    å´´
    0.09
    å»ĵ
    0.09
    æīĢå¾Ĺ
    0.09
    说æ³ķ
    0.09
    Activations Density 0.034%

    No Known Activations