© 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. 15777
    Prev
    Next
    INDEX
    Explanations

    public domain

    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
    ä¸įå¤ļ
    -0.25
    é«ĺæ°´å¹³
    -0.18
    plural
    -0.18
    .accel
    -0.18
     Lesb
    -0.18
    Liv
    -0.17
     Liv
    -0.17
     кнопк
    -0.17
    atories
    -0.17
    agrid
    -0.17
    POSITIVE LOGITS
    身åIJİ
    0.20
    éĺ¶
    0.20
    éĹ¨æ§Ľ
    0.20
    ç±į
    0.19
     Eig
    0.19
    roy
    0.19
    wu
    0.19
    轶
    0.19
    人çī©
    0.19
    æŧ
    0.19
    Activations Density 0.008%

    No Known Activations