© 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. 15846
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

    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
    ç»ĩ
    -0.21
    å®ıè§Ĥ
    -0.20
    imiter
    -0.20
    odie
    -0.20
    rong
    -0.20
    bek
    -0.19
    åĩ»æĿĢ
    -0.19
    recht
    -0.19
    (PARAM
    -0.19
    cket
    -0.19
    POSITIVE LOGITS
     fist
    0.21
    æ³¥
    0.21
    åĮħ
    0.21
    æĺ¥ç§ĭ
    0.19
    å¼ĢéĢļ
    0.18
    颡
    0.18
    干货
    0.18
     powers
    0.18
    æµģæ°´
    0.18
    æĢİä¹Īåģļ
    0.18
    Activations Density 0.003%

    No Known Activations