© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9308
    Prev
    Next
    INDEX
    Explanations

    advanced or additional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģķãģĪ
    -0.07
    _printer
    -0.07
     genie
    -0.07
    æĹ¥æĹ©ä¸Ĭ
    -0.07
    ëĬIJ
    -0.07
     cleanly
    -0.07
    严å®Ī
    -0.07
     easiest
    -0.06
     everywhere
    -0.06
     wherever
    -0.06
    POSITIVE LOGITS
     additional
    0.17
    追åĬł
    0.17
    additional
    0.16
    é¢Ŀå¤ĸ
    0.16
    é¢Ŀå¤ĸçļĦ
    0.15
     Additional
    0.15
     ì¶Ķê°Ģ
    0.14
    Additional
    0.14
     tambahan
    0.14
     zusätzliche
    0.13
    Activations Density 0.213%

    No Known Activations