© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    colors and descriptions

    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
    OfMonth
    -0.20
    æįĨç»ij
    -0.19
    _volume
    -0.18
    éĻ·åħ¥
    -0.18
     gig
    -0.18
    iente
    -0.18
     tether
    -0.18
    æĬ½
    -0.18
    rawer
    -0.18
     Thou
    -0.18
    POSITIVE LOGITS
    è§ĦåĪĴ建设
    0.19
    ãģ¾ãģŁãģ¯
    0.18
    åŁºæľ¬æĥħåĨµ
    0.18
    éĽĨåĽ¢èĤ¡ä»½
    0.18
    éĿ¢åŃIJ
    0.18
    veis
    0.18
    为主ä½ĵ
    0.18
    ÑĢÑĥÑģ
    0.18
    åºŁçī©
    0.18
    actable
    0.18
    Activations Density 0.027%

    No Known Activations