© 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. 2732
    Prev
    Next
    INDEX
    Explanations

    around orbits and rotation

    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´¯éĢļ
    -0.08
    æį£
    -0.08
    è¿ĽåŁİ
    -0.08
    åĩºæĿ¥
    -0.08
    æĵ¦
    -0.08
     Vent
    -0.08
     Conte
    -0.08
    西红
    -0.08
    Patch
    -0.08
    æĬķ
    -0.08
    POSITIVE LOGITS
    åĽ´ç»ķ
    0.21
    çݯç»ķ
    0.18
     вокÑĢÑĥг
    0.17
    åĽ´çĿĢ
    0.16
    around
    0.15
     Around
    0.14
    ä¸ĢåľĪ
    0.14
     around
    0.14
    Around
    0.14
    åij¨åĽ´
    0.14
    Activations Density 0.071%

    No Known Activations