© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10626
    Prev
    Next
    INDEX
    Explanations

    research and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æijĨ
    -0.20
    æĸĭ
    -0.20
    rame
    -0.20
    æĿ¡è§Ħå®ļ
    -0.20
    å®īæİĴ
    -0.20
    ä¸Ģå¼ł
    -0.19
    hek
    -0.19
    æĿ¡
    -0.18
    è£Ĥç¼Ŀ
    -0.18
    reads
    -0.18
    POSITIVE LOGITS
    çłĶåıij
    0.39
    çłĶåĪ¶
    0.34
    å¼Ģåıij
    0.32
    æĬĢæľ¯çłĶåıij
    0.31
    çłĶ究
    0.30
    产åĵģçłĶåıij
    0.29
    åĴĮæĬĢæľ¯
    0.29
    æĸ°æĬĢæľ¯
    0.29
    åĪĽæĸ°
    0.28
    çłĶåıijä¸Ńå¿ĥ
    0.27
    Activations Density 0.062%

    No Known Activations