© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    big, large, or sprawling descriptors

    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
    轻微
    -0.27
    å¤Ħå¢ĥ
    -0.25
    ç¾İ好çĶŁæ´»
    -0.23
    æĺ¯æľĢ好çļĦ
    -0.23
    _ORIGIN
    -0.21
    ноÑģÑĤ
    -0.21
    å°ıå·§
    -0.21
    pragma
    -0.21
    elles
    -0.21
    nameof
    -0.20
    POSITIVE LOGITS
     (>
    0.68
     bulky
    0.38
    (big
    0.37
    大çļĦ
    0.36
    /big
    0.35
    å·¨åŀĭ
    0.34
    Large
    0.34
    .Large
    0.33
     sprawling
    0.33
    -large
    0.32
    Activations Density 0.216%

    No Known Activations