© 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. 12112
    Prev
    Next
    INDEX
    Explanations

    Eastwood name

    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
    ä½ľæģ¯
    -0.18
     Gos
    -0.18
    orarily
    -0.17
     Fibonacci
    -0.17
    èįīæ¡Ī
    -0.17
    ael
    -0.17
    è¯ķ管
    -0.17
    arend
    -0.17
     Draft
    -0.17
    ffd
    -0.17
    POSITIVE LOGITS
    enton
    0.22
    .TryParse
    0.20
    mun
    0.19
    æ§İ
    0.18
     precip
    0.17
    寥
    0.17
    æĬĢæ³ķ
    0.17
    æĸ©
    0.17
    åħ±äº§
    0.17
    icap
    0.17
    Activations Density 0.002%

    No Known Activations