© 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. 27891
    Prev
    Next
    INDEX
    Explanations

    instructions and requirements

    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
    æĦļ
    -0.09
    åĢ¾
    -0.08
    å¥ł
    -0.08
    avicon
    -0.08
     Ry
    -0.08
    avs
    -0.08
    èĪį
    -0.08
     Avatar
    -0.08
     bye
    -0.08
    ä¸į容æĺĵ
    -0.08
    POSITIVE LOGITS
    两级
    0.10
    ongan
    0.10
     ÑĢеÑĪа
    0.09
    éħĴåºĹ
    0.09
    aine
    0.09
    otionEvent
    0.09
    é«ij
    0.09
    èĭ¥æĤ¨
    0.09
    红éħĴ
    0.09
    upal
    0.09
    Activations Density 0.037%

    No Known Activations