© 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. 15437
    Prev
    Next
    INDEX
    Explanations

    after punctuation

    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
     вне
    -0.19
    çļĦä¿¡ä»»
    -0.19
    ä¸Ģè¶Ł
    -0.19
    ä¸įéĹ´æĸŃ
    -0.19
    ISCO
    -0.19
     помог
    -0.18
    ITER
    -0.18
    ä¹Łåıªæľī
    -0.18
    并ä¸İ
    -0.18
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.18
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.73
     nor
    0.46
     sondern
    0.38
     anymore
    0.36
    nor
    0.36
    Nor
    0.31
    ä¹Łä¸įåı¯èĥ½
    0.30
     Nor
    0.30
     necessarily
    0.28
    ä¹Łä¸į
    0.26
    Activations Density 0.157%

    No Known Activations