© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    çķ°ãģªãĤĭ
    -0.18
     Hoy
    -0.18
    ä¸įåIJĮç¨ĭ度
    -0.17
    icker
    -0.17
    ehler
    -0.17
    ÑĮÑİ
    -0.17
    ä¸įé«ĺ
    -0.17
    ophile
    -0.16
    imson
    -0.16
    istic
    -0.16
    POSITIVE LOGITS
    /off
    0.25
     تÙħاÙħا
    0.24
    /in
    0.22
    /un
    0.22
    /on
    0.21
     khá»ıi
    0.21
    人åijĺ
    0.20
    /out
    0.20
    æĪĸèĢħ说
    0.19
    loading
    0.18
    Activations Density 0.031%

    No Known Activations