© 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. 33826
    Prev
    Next
    INDEX
    Explanations

    details and complexities

    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
    æĭīæĸ¯
    -0.10
    ä¸įçĽ¸ä¿¡
    -0.09
    综åIJĪæĢ§
    -0.09
    åľ¨åĽ½åĨħ
    -0.09
    íĦ°
    -0.09
    æīĵåĩº
    -0.09
    æĺ¯æľĢ好çļĦ
    -0.09
    å¿ĥ缮
    -0.09
    oreach
    -0.08
    çľł
    -0.08
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.13
     details
    0.12
     intric
    0.11
    详æĥħ
    0.11
     complexities
    0.11
    details
    0.11
     specifics
    0.10
    Details
    0.10
     Details
    0.10
    究竣
    0.10
    Activations Density 0.093%

    No Known Activations