© 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. 36509
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
    æĭ¿æĿ¥
    -0.10
    еÑĩа
    -0.10
    第ä¸Ģ天
    -0.10
    åĨĴ
    -0.09
    åĩºåħ¥
    -0.09
    åľ¨åĽ½å¤ĸ
    -0.09
    ä¹Łåı¯
    -0.08
    è¿ĩå¾Ĺ
    -0.08
    æľĢåħĪ
    -0.08
    è¿ĽæĿ¥
    -0.08
    POSITIVE LOGITS
    ibase
    0.10
    修订
    0.09
    大ä¼Ĺ
    0.09
    TEMPL
    0.08
    essen
    0.08
    TemplateName
    0.08
    è¡Į使
    0.08
    reater
    0.08
    Templates
    0.08
    æĽ
    0.08
    Activations Density 0.186%

    No Known Activations