© 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. 27387
    Prev
    Next
    INDEX
    Explanations

    og:title or og:image

    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
    大å±Ģ
    -0.09
    aries
    -0.09
    éĶ¢
    -0.08
    ä»Ģä¹ĪæĦıæĢĿ
    -0.08
    TagName
    -0.08
    禺
    -0.08
    ôme
    -0.08
    IJ
    -0.08
    .DOM
    -0.08
    cus
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    ness
    0.10
    è¡Į人
    0.09
    licer
    0.09
    ../../
    0.09
    0.09
    wald
    0.09
    ãĥ¥
    0.09
    idebar
    0.09
    ieval
    0.09
    Activations Density 0.019%

    No Known Activations