© 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. 13401
    Prev
    Next
    INDEX
    Explanations

    say that, to say the least, at best

    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¯ī
    -0.23
    è¯ģæĺİ
    -0.20
     whip
    -0.19
    èĩªåıij
    -0.19
    CTS
    -0.19
    åİĺ
    -0.18
    ub
    -0.18
    è§īå¾Ĺèĩªå·±
    -0.18
     INCLUDE
    -0.18
    ä¸Ńå°ıåŀĭ
    -0.18
    POSITIVE LOGITS
    ton
    0.19
    _INITIALIZ
    0.19
    æŶä¸į
    0.18
    .tpl
    0.17
    illas
    0.17
    -Ray
    0.17
    awesome
    0.17
    íıīê°Ģ
    0.17
    æ¦Ĥæĭ¬
    0.17
    brook
    0.16
    Activations Density 0.006%

    No Known Activations