© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35707
    Prev
    Next
    INDEX
    Explanations

    research and education

    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
    ÑĪин
    -0.09
    aded
    -0.09
    -Russian
    -0.08
    ($)
    -0.08
    Reached
    -0.08
    好人
    -0.08
    è®Ńç»ĥ
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    踢
    -0.08
    hin
    -0.08
    POSITIVE LOGITS
    ç«Ļ
    0.11
    åĿŀ
    0.10
    åĬ©çIJĨ
    0.10
    å¹½
    0.09
    åŁºæľ¬éĿ¢
    0.09
    漪
    0.09
    课é¢ĺ
    0.09
    çłĶ究åijĺ
    0.09
    åĿİ
    0.09
    表æĺİ
    0.08
    Activations Density 0.108%

    No Known Activations