© 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. 48019
    Prev
    Next
    INDEX
    Explanations

    muscle mass

    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
    åį«çĶŁ
    -0.10
    å®ķ
    -0.10
    åħ¨æ°ij
    -0.09
    ifter
    -0.09
    跨度
    -0.09
     Classics
    -0.09
    æŃ¥æŃ¥
    -0.09
    屡
    -0.09
    .ErrorCode
    -0.09
    ailable
    -0.09
    POSITIVE LOGITS
    èĤĮèĤī
    0.12
     muscle
    0.10
     muscular
    0.10
    壮
    0.09
     muscles
    0.09
     Ùħد
    0.09
    åģļ强
    0.09
     khá»iji
    0.09
    ä½ĵéĩį
    0.09
    壯
    0.09
    Activations Density 0.111%

    No Known Activations