© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40162
    Prev
    Next
    INDEX
    Explanations

    position or pose

    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
    Negative Logits
    rated
    -0.10
    ç¥Ĺ
    -0.09
    .Target
    -0.09
    æĢ§è´¨
    -0.09
    egov
    -0.09
     nut
    -0.09
    èĽĭç³ķ
    -0.09
    åį°è±¡
    -0.08
    絡
    -0.08
     Jud
    -0.08
    POSITIVE LOGITS
    姿åĬ¿
    0.21
    姿
    0.16
    姿æĢģ
    0.15
     position
    0.14
     posture
    0.13
    çļĦ姿æĢģ
    0.13
    position
    0.13
    Position
    0.13
    -position
    0.13
     Positions
    0.13
    Activations Density 0.134%

    No Known Activations