© 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. 63171
    Prev
    Next
    INDEX
    Explanations

    time periods before dates

    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
    åĪ¶è£ģ
    -0.09
    ç»Ĵ
    -0.09
    ÑĢаг
    -0.09
    ç¾ļ
    -0.09
     воÑĤ
    -0.08
    fon
    -0.08
    åIJ¸æĶ¶
    -0.08
    æ£ī
    -0.08
    åİŁæľī
    -0.08
    ITTER
    -0.08
    POSITIVE LOGITS
    å¾Ģ
    0.09
    ological
    0.09
    -minded
    0.09
    ç»ĵåIJĪ
    0.08
    0.08
    ạc
    0.08
    æĪĸå¤ļ
    0.08
    ç½Ł
    0.08
    çļĦä¸Ģ大
    0.08
    wap
    0.08
    Activations Density 0.010%

    No Known Activations