© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63878
    Prev
    Next
    INDEX
    Explanations

    code constructs or delimiters

    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
    uille
    -0.08
    Vert
    -0.07
    .Singleton
    -0.07
    èľĤ
    -0.07
    -align
    -0.07
    ille
    -0.07
    èİ«è¿ĩäºİ
    -0.07
     lho
    -0.07
    ehl
    -0.07
     *.*
    -0.07
    POSITIVE LOGITS
    ìĬ¹
    0.07
    表çİ°
    0.07
    士
    0.07
    eru
    0.07
    ather
    0.07
    çĶŁäº§è¿ĩç¨ĭ
    0.06
    ominator
    0.06
    uty
    0.06
    ä¸įæĶ¹
    0.06
    mek
    0.06
    Activations Density 0.092%

    No Known Activations