© 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. 35562
    Prev
    Next
    INDEX
    Explanations

    tag/title/html

    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¸Ĭå®ĺ
    -0.09
    iveness
    -0.09
    æĸĻ
    -0.08
    å®ŀæĸ½æĸ¹æ¡Ī
    -0.08
    干货
    -0.08
    èŁĬ
    -0.08
     ive
    -0.08
    éĻIJãĤĬ
    -0.08
    å°±æĥ³
    -0.07
    RTC
    -0.07
    POSITIVE LOGITS
    _COOKIE
    0.11
    ATTLE
    0.09
    _CHIP
    0.09
     tầ
    0.09
    .gwt
    0.09
    èIJĿ
    0.08
    olumbia
    0.08
    æłĹ
    0.08
    .tx
    0.08
    (getClass
    0.08
    Activations Density 0.352%

    No Known Activations