© 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. 41489
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation

    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
    ...,
    -0.07
    ...",
    -0.07
    ä¸İåħ¶
    -0.06
    缮
    -0.06
    ...
    -0.06
    -
    -0.06
    );//
    -0.06
    ;//
    -0.06
     ...
    -0.06
     ...,
    -0.06
    POSITIVE LOGITS
    åı¤å±ĭ
    0.08
    idel
    0.08
    ?v
    0.08
    ywa
    0.08
    ستÙĬر
    0.08
    CellStyle
    0.08
    à¹Ģราสà¸Ļัà¸ļสà¸Ļุà¸Ļ
    0.08
    åįķåŃIJ
    0.08
    çī¹å°Ķ
    0.08
    overy
    0.08
    Activations Density 0.013%

    No Known Activations