© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    `ran from`, `airs live on`, `rose in August`, `located in`

    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
     sud
    -0.18
    è·Ľ
    -0.18
    qus
    -0.18
    _COMMENT
    -0.17
    åķĬ
    -0.17
    嵯
    -0.17
    ä¸į论æĺ¯
    -0.17
    cliffe
    -0.17
    åĪ°åºķ
    -0.17
    èĢĮåĩº
    -0.17
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.49
    åĪĻ
    0.44
    åīĩ
    0.40
    ä¹Łæĺ¯å¦ĤæѤ
    0.39
     likewise
    0.33
     similarly
    0.31
    åı¦æľī
    0.30
    æĽ´æĺ¯
    0.30
     meanwhile
    0.29
     ÑĤоже
    0.28
    Activations Density 0.181%

    No Known Activations