© 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. 52704
    Prev
    Next
    INDEX
    Explanations

    questions starting with "is"

    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
    ä¸į该
    -0.09
    eph
    -0.08
    æİĴè¡Į
    -0.08
    nda
    -0.08
    irk
    -0.08
     pant
    -0.08
    ibo
    -0.08
     Ñģов
    -0.08
    rary
    -0.08
    vidia
    -0.08
    POSITIVE LOGITS
    大çīĩ
    0.08
    ä¸ĢåĪĢ
    0.08
    _MAXIMUM
    0.08
    à´´
    0.08
    èĬĹ
    0.08
    缶
    0.08
    çĿĢçľ¼
    0.08
    <[
    0.08
    绿水
    0.08
    è¿ĻåĿĹ
    0.08
    Activations Density 0.003%

    No Known Activations