© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21538
    Prev
    Next
    INDEX
    Explanations

    free/end/game or from

    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
    æįº
    -0.10
    èĤĮ
    -0.09
    çĶŁäº§å·¥èīº
    -0.09
    ä¸įä¸Ĭ
    -0.09
    è¿ŀè¿ŀ
    -0.09
    ç§ijæĬĢè¿ĽæŃ¥
    -0.09
    éĢļé£İ
    -0.09
    çİ©æ³ķ
    -0.09
    æľīä¸Ģå®ļ
    -0.09
    çŁĽçĽ¾
    -0.09
    POSITIVE LOGITS
    èĿĩ
    0.09
    illi
    0.09
     remainder
    0.08
    Raster
    0.08
    .jquery
    0.08
    onica
    0.08
    antage
    0.08
    çºĮ
    0.08
    ạ
    0.07
    ilia
    0.07
    Activations Density 0.001%

    No Known Activations