© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21162
    Prev
    Next
    INDEX
    Explanations

    upper/lower body parts or actions

    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
    ç»Ī
    -0.13
    人工
    -0.09
     comm
    -0.09
    dar
    -0.09
    声
    -0.09
    ABS
    -0.09
    çµĤ
    -0.08
     кÑĥда
    -0.08
    _reports
    -0.08
    èģ²
    -0.08
    POSITIVE LOGITS
    éªł
    0.10
    ç½Ĺ马
    0.10
    举è¡ĮäºĨ
    0.09
    篮
    0.09
    èĪĮ头
    0.09
    èĢģå©Ĩ
    0.09
    åĩ»
    0.09
    пÑĢовод
    0.09
    èĹIJ
    0.09
     Pruitt
    0.08
    Activations Density 0.118%

    No Known Activations