© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    potential, normal, proper, or lower X

    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
    絡
    -0.27
    çļĦä¸įåIJĮ
    -0.27
    éĢĤåIJĪèĩªå·±
    -0.26
    ä¸įåIJĮçļĦ
    -0.24
     Different
    -0.23
    ä¸įèĪį
    -0.23
    æµ·æ£ł
    -0.23
    æĭĦ
    -0.22
     rarity
    -0.22
     AP
    -0.21
    POSITIVE LOGITS
    åİŁæľ¬
    0.43
    åİŁæľīçļĦ
    0.42
    æľ¬æĿ¥
    0.37
     otherwise
    0.35
    otherwise
    0.34
    åİŁæľī
    0.34
    åİŁåħĪ
    0.32
    æľ¬æĿ¥å°±
    0.31
    æŃ£å¸¸çļĦ
    0.31
     rightfully
    0.29
    Activations Density 0.212%

    No Known Activations