© 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. 16551
    Prev
    Next
    INDEX
    Explanations

    granules

    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
    çļĦçľ¼çĿĽ
    -0.19
    è¦ļ
    -0.19
    åĽ½éĻħæľºåľº
    -0.19
    çļĦãģ«ãģ¯
    -0.19
    éļĨ
    -0.19
    Eye
    -0.18
    éĩijåŃĹå¡Ķ
    -0.18
    éªĢ
    -0.18
    åĽ´çĿĢ
    -0.18
    åijĬè¯īæĪij们
    -0.18
    POSITIVE LOGITS
    /bind
    0.20
    Runtime
    0.19
     &(
    0.19
    å¹³æŶ
    0.19
    ç¨ĢåľŁ
    0.18
    çĶµåĻ¨
    0.18
    cko
    0.18
    subtype
    0.18
    enerator
    0.18
    actics
    0.18
    Activations Density 0.003%

    No Known Activations