© 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. 5619
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

    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
    ç§įç§į
    -0.09
    ç¤ģ
    -0.08
    ัà¸Ļ
    -0.08
    ç¦ıçĶ°
    -0.08
    y
    -0.08
    hev
    -0.08
    inha
    -0.08
    èı°
    -0.08
    asd
    -0.08
    defer
    -0.08
    POSITIVE LOGITS
    ваÑĤ
    0.09
    traîn
    0.09
    Ø´ÙĨ
    0.09
    stances
    0.09
    prise
    0.09
    каÑĢ
    0.09
     McMahon
    0.08
     Watkins
    0.08
    ippi
    0.08
    лав
    0.08
    Activations Density 0.037%

    No Known Activations