© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    don't or doesn't

    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
    æݨå¼Ģ
    -0.22
    ason
    -0.21
    ned
    -0.19
     hy
    -0.19
    hy
    -0.19
    ULO
    -0.18
    åĩŃ
    -0.18
     lac
    -0.18
    itial
    -0.18
    ral
    -0.18
    POSITIVE LOGITS
    æŃ¥æŃ¥
    0.20
    奸
    0.20
    åĴ¬
    0.19
    ä¸Ŀä¸Ŀ
    0.19
     chữ
    0.18
    è´¨éĩı管çIJĨ
    0.18
    _vert
    0.18
    cth
    0.18
    鼶ç¢İ
    0.18
     Quincy
    0.18
    Activations Density 0.013%

    No Known Activations