© 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. 31036
    Prev
    Next
    INDEX
    Explanations

    vacant or empty space

    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
    era
    -0.10
    åħ¬è®¤çļĦ
    -0.10
    orable
    -0.09
    赦
    -0.09
    unte
    -0.09
    è¿ĺåİŁ
    -0.09
    级
    -0.08
    è±¢
    -0.08
    è¿Ľåħ¥äºĨ
    -0.08
    åħ³æĢĢ
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.09
    вели
    0.09
    åĩºåİĤ
    0.09
    è¾ĥå¤ļ
    0.09
    (empty
    0.09
     weighted
    0.09
    çŀħ
    0.09
    _modes
    0.08
    骡
    0.08
    åĵĤ
    0.08
    Activations Density 0.054%

    No Known Activations