© 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. 55364
    Prev
    Next
    INDEX
    Explanations

    calendar events and appointments

    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
    ç¹ģèį£
    -0.11
    è´©
    -0.09
    amac
    -0.09
    ä¸įèĤ¯
    -0.09
    IfNeeded
    -0.08
     Trom
    -0.08
    æ¯ĶæĪij
    -0.08
    mort
    -0.08
    ç»Ī
    -0.08
     Toll
    -0.08
    POSITIVE LOGITS
    bcc
    0.09
    VO
    0.09
    åİļ度
    0.09
    åĬ¨åĬĽçĶµæ±ł
    0.09
    åIJįçīĩ
    0.09
    èĵĸ
    0.09
    .putExtra
    0.08
    repeat
    0.08
     calendars
    0.08
    èݲèĬ±
    0.08
    Activations Density 0.103%

    No Known Activations