© 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. 59258
    Prev
    Next
    INDEX
    Explanations

    writing style

    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
    大åĬĽåıijå±ķ
    -0.08
     getContent
    -0.08
    pling
    -0.08
    åĿı
    -0.08
     Nex
    -0.08
    ä¹ĭäºĭ
    -0.08
    urge
    -0.08
    nw
    -0.08
    社ä¼ļ
    -0.08
    _TRI
    -0.08
    POSITIVE LOGITS
    é£İæł¼
    0.19
    é¢¨æł¼
    0.17
     style
    0.14
    style
    0.13
    STYLE
    0.13
    	style
    0.13
     approach
    0.13
     Style
    0.13
    _STYLE
    0.12
    ä½ľé£İ
    0.12
    Activations Density 0.082%

    No Known Activations