© 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. 12677
    Prev
    Next
    INDEX
    Explanations

    names or titles

    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
    åŃº
    -0.21
    омеÑĢ
    -0.19
    istical
    -0.19
    è¹ij
    -0.19
    andon
    -0.18
    åį³ä½¿æĺ¯
    -0.17
    ç®Ģ缴æĺ¯
    -0.17
    ÄĽ
    -0.17
    tas
    -0.17
    suite
    -0.17
    POSITIVE LOGITS
    ç»ĨåĪĻ
    0.20
    .Variable
    0.18
    çļĦæĿĥåĪ©
    0.18
    late
    0.17
    quine
    0.17
    มา
    0.17
    æ°´åŁŁ
    0.17
    sheets
    0.17
    .connected
    0.17
     cro
    0.17
    Activations Density 0.001%

    No Known Activations