© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15304
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by capitalized word

    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
    iled
    -0.21
     assort
    -0.19
    wald
    -0.18
    steen
    -0.18
    èŀįåIJĪ
    -0.18
    YA
    -0.18
    éĺ¿å¯Į
    -0.18
    renc
    -0.18
     Inch
    -0.18
    æīĵ交
    -0.18
    POSITIVE LOGITS
    éĹ¨æ§Ľ
    0.25
    åIJįåįķ
    0.21
    æ¯Ķçİĩ
    0.21
    ä¾ĭå¦Ĥ
    0.20
    ä»ĸ们æĺ¯
    0.20
    ä¸įå¤ļ
    0.20
    ä¹Łåıªæľī
    0.19
    ä»ħæľī
    0.19
    æľīåĵªäºĽ
    0.19
    æķ°éĩı
    0.19
    Activations Density 0.172%

    No Known Activations