© 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. 14508
    Prev
    Next
    INDEX
    Explanations

    error messages and issues

    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
    oad
    -0.20
    ç§ijæķĻ
    -0.18
    oose
    -0.18
    å²Ĺä½į
    -0.18
    è³ĩ
    -0.18
    å¤īãĤıãĤĭ
    -0.17
     pros
    -0.17
    ä¸įåıĬ
    -0.17
    çŃ¾ç½²
    -0.17
     tapes
    -0.17
    POSITIVE LOGITS
    lek
    0.22
    éĩįéĩį
    0.21
    .statusText
    0.19
    æĪĸ许æĺ¯
    0.19
    说è¯Ŀ
    0.19
    ouston
    0.18
    Resolved
    0.18
    jak
    0.18
    ordinate
    0.18
    Occurred
    0.18
    Activations Density 0.064%

    No Known Activations