© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2544
    Prev
    Next
    INDEX
    Explanations

    examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     others
    -0.28
    æŀľ
    -0.25
    åį´
    -0.25
     sexes
    -0.24
     ÑĤоже
    -0.23
     nonetheless
    -0.23
     then
    -0.23
    ãģĵãĤĮãģĮ
    -0.23
     otherwise
    -0.23
    _then
    -0.23
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.36
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.31
    åľ¨è¿ĩåİ»
    0.28
    æ¯ıå½ĵ
    0.27
    åľ¨ä»Ĭå¹´
    0.27
    åį³ä¾¿æĺ¯
    0.27
    ä¸įä½Ĩ
    0.26
    è¶ģçĿĢ
    0.25
    缸æ¯Ķäºİ
    0.25
    åľ¨ä¸Ģ个
    0.24
    Activations Density 0.148%

    No Known Activations