© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    Big Ten Conference

    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
     aisle
    -0.20
    æ¾ľ
    -0.20
    å··
    -0.19
    島
    -0.19
     alley
    -0.19
    æĿ¥èĩª
    -0.19
    æIJĢ
    -0.18
    磻
    -0.18
    å²Ľ
    -0.18
    äºŃ
    -0.18
    POSITIVE LOGITS
    大大å°ıå°ı
    0.21
    æĪIJåijĺ
    0.21
    steam
    0.19
    atives
    0.19
    member
    0.18
    æķ´æķ´
    0.18
    éĻIJéĩı
    0.18
    ç¿»å¼Ģ
    0.17
    acias
    0.17
    çĴĭ
    0.17
    Activations Density 0.003%

    No Known Activations