© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12958
    Prev
    Next
    INDEX
    Explanations

    chief officers

    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
    太åIJİ
    -0.21
    模ç³Ĭ
    -0.20
     ìĿ´ëŁ¬
    -0.20
    ½æķ°
    -0.19
    éģĩåĪ°
    -0.18
    Äħc
    -0.18
    éħ¥
    -0.18
    _lookup
    -0.18
    Abs
    -0.18
    iskey
    -0.18
    POSITIVE LOGITS
    éĿŀ常好
    0.21
     Morton
    0.20
    aggio
    0.20
    ä»ĬåĽŀãģ¯
    0.20
    æľ¬æľŁ
    0.20
    该æ¡Ī
    0.19
    ä¸Ģæ³¢
    0.19
    æŃ¤æ¬¡
    0.19
    æѤæ¡Ī
    0.18
    ami
    0.18
    Activations Density 0.104%

    No Known Activations