© 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. 11924
    Prev
    Next
    INDEX
    Explanations

    Zlib/license, Verilog Lexer

    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
    äºĺ
    -0.21
    sed
    -0.20
    æ¡Ģ
    -0.20
    ding
    -0.19
    Spread
    -0.19
    spread
    -0.19
    éĵ«
    -0.18
    è¨ĩ
    -0.18
    AO
    -0.18
    alent
    -0.18
    POSITIVE LOGITS
    级
    0.23
    nock
    0.19
    éģ¿
    0.19
    çħ¨
    0.19
    æ°´æĻ¶
    0.18
    ç§Łè½¦
    0.18
    å¹ķ
    0.17
    fare
    0.17
    uchi
    0.17
    æł¹æºIJ
    0.17
    Activations Density 0.001%

    No Known Activations