© 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. 48087
    Prev
    Next
    INDEX
    Explanations

    physical activity

    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
    趴
    -0.10
    çĤķ
    -0.10
    è°¦
    -0.09
    梦è§ģ
    -0.09
    çī¢
    -0.09
    å®´
    -0.08
    èįŁ
    -0.08
    件
    -0.08
    æĺ¯æĢİæł·
    -0.08
    åıī
    -0.08
    POSITIVE LOGITS
    æķ£æŃ¥
    0.13
    漫æŃ¥
    0.13
     stroll
    0.12
    å¾ľ
    0.12
     walks
    0.11
    å¾ĺå¾Ĭ
    0.11
    ç»ķ
    0.10
    .walk
    0.10
     пÑĢог
    0.10
     walk
    0.10
    Activations Density 0.027%

    No Known Activations