© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10642
    Prev
    Next
    INDEX
    Explanations

    generated code or text

    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
    è¡Įä¸ļåıijå±ķ
    -0.20
    ç±´
    -0.20
    ä¾ĽéľĢ
    -0.19
    ä¸Ģ对ä¸Ģ
    -0.19
    èĥ«
    -0.18
    度
    -0.18
    à¸ķà¸ģ
    -0.18
    ä¸īçĻ¾
    -0.18
    å¤ļæķ°
    -0.17
    ided
    -0.17
    POSITIVE LOGITS
     оÑĦоÑĢмлен
    0.19
    chez
    0.19
    Unnamed
    0.19
    æĢ¯
    0.19
    人家
    0.19
    lij
    0.18
    archs
    0.18
    ogs
    0.18
    TZ
    0.18
    angers
    0.17
    Activations Density 0.005%

    No Known Activations