© 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. 54793
    Prev
    Next
    INDEX
    Explanations

    different formats

    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»įæĺ¯
    -0.09
    仪
    -0.09
    åħ¨åĮº
    -0.09
    ä¾ĿçĦ¶
    -0.09
    åħ¨æĿij
    -0.08
    sgi
    -0.08
    aring
    -0.08
    ä¸ĵåĮº
    -0.08
    aging
    -0.08
    GI
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.11
    å¾Ī好çļĦ
    0.11
    å¾Īä¸įéĶĻ
    0.11
    å¾Īæ£Ĵ
    0.10
    ä¸įéĶĻçļĦ
    0.10
    åIJĦæľī
    0.10
    ç¾İ好
    0.10
    iban
    0.10
    åIJĦèĩªçļĦ
    0.10
    igator
    0.09
    Activations Density 0.066%

    No Known Activations