© 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. 16312
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    finity
    -0.21
     Twice
    -0.19
     Wings
    -0.19
    ÑĤин
    -0.18
    FINITY
    -0.18
    ython
    -0.17
     Preference
    -0.17
    å¼ıçļĦ
    -0.17
    odon
    -0.17
    ä¸Ģçīĩ
    -0.17
    POSITIVE LOGITS
    åIJĦç±»
    0.24
    è¿Ļ两ç§į
    0.23
    æ°´åĪĨ
    0.21
     energy
    0.21
     various
    0.21
    诸å¦Ĥ
    0.20
    åIJĦç§įåIJĦæł·
    0.20
     either
    0.20
     both
    0.20
    æł¸å¿ĥ
    0.19
    Activations Density 0.361%

    No Known Activations