© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    stock tickers like CS

    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
    åĵĨ
    -0.19
    أس
    -0.19
    alsa
    -0.18
    (machine
    -0.17
    ilon
    -0.17
    éĢļè¡Įè¯ģ
    -0.17
    çľł
    -0.17
    å§Ķ书记
    -0.17
    ä½ľæģ¯
    -0.17
    æ¨Ĺ
    -0.17
    POSITIVE LOGITS
    æĭīå¼Ģ
    0.25
    è´¢
    0.21
    æ¥Ķ
    0.20
    æµ®
    0.20
    è´¢åĬ¡ç®¡çIJĨ
    0.20
    okit
    0.19
    è´¢åĬĽ
    0.18
     lac
    0.18
    å¼±çĤ¹
    0.18
    è´¢åĬ¡
    0.18
    Activations Density 0.001%

    No Known Activations