© 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. 49014
    Prev
    Next
    INDEX
    Explanations

    inadvertently copied/backing

    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
    屡
    -0.09
    åĩłä¹İæīĢæľī
    -0.09
    åĩłä¹İ
    -0.09
    ä¸įåģľ
    -0.09
    äºĨä¸Ģç³»åĪĹ
    -0.09
    å¤©åľ°
    -0.08
    åĩºäºĨ
    -0.08
    ä¸ĬäºĨ
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    èĢĮéĿŀ
    -0.08
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.16
    æľīä»»ä½ķ
    0.13
     nor
    0.12
     someday
    0.11
    æĪĸåħ¶ä»ĸ
    0.11
    ä¹Łä¸įè¦ģ
    0.11
    太ä¹ħ
    0.10
    åĪ°æŶåĢĻ
    0.10
    nor
    0.10
    èĢĮæĺ¯
    0.10
    Activations Density 0.183%

    No Known Activations