© 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. 39132
    Prev
    Next
    INDEX
    Explanations

    muscular physique and body parts

    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
    è´¡
    -0.09
    ctl
    -0.09
    åļı
    -0.09
    nik
    -0.08
    lectic
    -0.08
    igt
    -0.08
    åģ·
    -0.08
    æĶĺ
    -0.08
    apt
    -0.08
    æ§Ľ
    -0.08
    POSITIVE LOGITS
    èĤĮèĤī
    0.16
    åģ¥èº«
    0.14
    éĶ»çĤ¼
    0.13
     muscular
    0.12
     muscles
    0.12
    å¡ijéĢł
    0.12
     physique
    0.11
     muscle
    0.11
    ä¼ı
    0.11
    线æĿ¡
    0.11
    Activations Density 0.082%

    No Known Activations