© 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. 31707
    Prev
    Next
    INDEX
    Explanations

    muscle relaxation and conditions

    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
    è¾¹ä¸Ĭ
    -0.09
    åĩºæīĭ
    -0.09
    èĤĩäºĭ
    -0.09
    åijķ
    -0.08
     Marcel
    -0.08
    ä¸įçĶĺ
    -0.08
    elve
    -0.08
    _Handler
    -0.08
     crush
    -0.08
     Walsh
    -0.08
    POSITIVE LOGITS
    æĶ¾æĿ¾
    0.13
    ç´§å¼ł
    0.12
    èĤĮèĤī
    0.11
     Relax
    0.11
     relaxation
    0.10
    íħIJ
    0.09
     ÑĢеакÑĨи
    0.09
    ç¬ij容
    0.09
     tense
    0.09
     relaxing
    0.09
    Activations Density 0.112%

    No Known Activations