© 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. 12704
    Prev
    Next
    INDEX
    Explanations

    name or term

    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
    åIJįåı«
    -0.26
    称为
    -0.22
    称ä¹ĭ为
    -0.22
    被称为
    -0.21
    éĦ¢
    -0.20
    åIJį为
    -0.20
     tÃŃch
    -0.20
    åı«åģļ
    -0.19
     indent
    -0.19
    pv
    -0.19
    POSITIVE LOGITS
    zheimer
    0.20
    好äºĭ
    0.20
    ä½ľä¸ºä¸Ģç§į
    0.19
    uddle
    0.19
    _articles
    0.18
    udging
    0.18
    uplic
    0.18
    vro
    0.18
    idan
    0.18
    _used
    0.17
    Activations Density 0.120%

    No Known Activations