© 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. 12562
    Prev
    Next
    INDEX
    Explanations

    US, British names

    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
    伶
    -0.08
    anti
    -0.07
    isor
    -0.07
    å±Ģ
    -0.07
     ê²
    -0.07
    sher
    -0.06
    Submit
    -0.06
    ãĤ³ãĥ³ãĥĪ
    -0.06
    骨质çĸıæĿ¾
    -0.06
     Rav
    -0.06
    POSITIVE LOGITS
    大ä¸Ń
    0.07
    urgi
    0.07
    ondi
    0.07
    _IOS
    0.07
    اغ
    0.06
    uard
    0.06
    çĿģ
    0.06
    éģĵåºľ
    0.06
    waard
    0.06
    表示èĩªå·±
    0.06
    Activations Density 0.004%

    No Known Activations