© 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. 3650
    Prev
    Next
    INDEX
    Explanations

    file format

    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°Ł
    -0.10
    èµĦæºIJéħįç½®
    -0.10
    常å§Ķä¼ļ
    -0.09
    ä¸Ńæĸ¹
    -0.09
    /feed
    -0.09
    ä¸Ģéĥ¨
    -0.09
    èī°è¾Ľ
    -0.08
    æĶ¾åĪ°
    -0.08
    èģĶæĥ³
    -0.08
    ä¸Ģ对
    -0.08
    POSITIVE LOGITS
    æł¼å¼ı
    0.23
     format
    0.19
     formats
    0.18
    Format
    0.16
     formato
    0.16
    format
    0.15
    -format
    0.15
     Format
    0.14
    _format
    0.14
    FORMAT
    0.13
    Activations Density 0.185%

    No Known Activations