© 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. 2390
    Prev
    Next
    INDEX
    Explanations

    sound quality

    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
    å¼ıçļĦ
    -0.26
    æ¸İ
    -0.23
    åľºéĿ¢
    -0.23
    èĩĨ
    -0.23
    æĹ¥æľŁ
    -0.22
    æĿ¥ä¸įåıĬ
    -0.22
    ZH
    -0.22
    åĬłå¿«æİ¨è¿Ľ
    -0.22
    <Date
    -0.22
    èĩªåĬ¨åĮĸ
    -0.21
    POSITIVE LOGITS
     quality
    0.40
    quality
    0.32
     qualities
    0.30
     Quality
    0.29
    _quality
    0.28
     comprom
    0.28
    qualities
    0.28
     QUAL
    0.28
     каÑĩеÑģÑĤво
    0.27
     characteristics
    0.27
    Activations Density 0.039%

    No Known Activations