© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    accuracy or errors

    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
     MethodInfo
    -0.20
    弯
    -0.20
    ç¼Ĺ
    -0.20
    ksen
    -0.20
    /latest
    -0.19
     sourceMapping
    -0.19
    å¼¯æĽ²
    -0.19
    èĿĮ
    -0.18
     unanimously
    -0.18
    ény
    -0.18
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.20
     Hed
    0.19
    ä¸ĬæĿ¥
    0.19
    lotte
    0.18
    ä¸įä¸ĭ
    0.18
    antry
    0.17
    pars
    0.17
    ures
    0.17
    oidal
    0.17
    Title
    0.17
    Activations Density 0.012%

    No Known Activations