© 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. 10721
    Prev
    Next
    INDEX
    Explanations

    letters picked

    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
    ardin
    -0.23
    apas
    -0.21
    è¾ĵç»Ļ
    -0.20
    breaker
    -0.20
    icont
    -0.19
    á»ĵng
    -0.19
    UDA
    -0.19
    ational
    -0.18
    èĬ
    -0.18
    æµ·æ¹¾
    -0.18
    POSITIVE LOGITS
    çļĦåIJĦç§į
    0.20
    大å¹ħ
    0.19
    èıľèĤ´
    0.18
    åħ±éĿĴåĽ¢
    0.17
    ideshow
    0.17
    elow
    0.17
    许åı¯
    0.17
     Katz
    0.17
    çĪ±åIJĥ
    0.17
    avatars
    0.17
    Activations Density 0.003%

    No Known Activations