© 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. 34016
    Prev
    Next
    INDEX
    Explanations

    racing events

    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¸įå°½
    -0.09
     bere
    -0.09
    èĵ¼
    -0.09
    ocard
    -0.09
     pivot
    -0.08
    licit
    -0.08
    éģįå¸ĥ
    -0.08
    æĶ¿åħļ
    -0.08
    _MetaData
    -0.08
     Leopard
    -0.08
    POSITIVE LOGITS
    thon
    0.09
    ylv
    0.08
    ä¸Ģ身
    0.08
    æĪIJ绩åįķ
    0.08
    å±Ĥå±Ĥ
    0.08
    /dir
    0.08
    nonnull
    0.08
    wow
    0.08
     Wow
    0.08
     Sylv
    0.08
    Activations Density 0.006%

    No Known Activations