© 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. 5471
    Prev
    Next
    INDEX
    Explanations

    html tag start

    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
    ised
    -0.10
    è¯ķè¯ķ
    -0.09
    atan
    -0.09
    ied
    -0.09
    åı²è¯Ĺ
    -0.09
    åĨ¼
    -0.08
    澧
    -0.08
    çļĦåIJĦç§į
    -0.08
    ableObject
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    POSITIVE LOGITS
     Ow
    0.10
    缮çļĦæĺ¯
    0.09
    ä¸įçĦ¶
    0.08
    èī¯å¿ĥ
    0.08
    psilon
    0.08
    é»į
    0.08
    agi
    0.08
    azo
    0.08
    outu
    0.08
     {[
    0.08
    Activations Density 2.665%

    No Known Activations