© 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. 16595
    Prev
    Next
    INDEX
    Explanations

    electronics and devices

    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¿ĶåĽŀæIJľçĭIJ
    -0.13
    .Generated
    -0.13
     ÐIJлекÑģан
    -0.12
    strstr
    -0.12
    	RTLR
    -0.11
     ÐĶм
    -0.11
    .generated
    -0.11
    /generated
    -0.11
    à²Ĭ
    -0.11
    æīĬ
    -0.11
    POSITIVE LOGITS
    使çĶ¨ç¶²è·¯
    0.19
    çķ¶æĤ¨åľ¨
    0.18
    該使çĶ¨èĢħ
    0.17
    çŀŃ解並
    0.15
    éĽ»è©±åıĬ
    0.15
    æľįåĭĻæĪĸ
    0.15
    ä»Ĭ天å°ıç¼ĸ
    0.15
    使çĶ¨èĢħæĪĸ
    0.14
    åĢĭ人è³ĩè¨Ĭ
    0.14
    åĶ¿
    0.14
    Activations Density 99.150%

    No Known Activations