© 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. 2003
    Prev
    Next
    INDEX
    Explanations

    index: or "

    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
    yro
    -0.07
    ÏħÏĩ
    -0.07
    otov
    -0.07
    ulihan
    -0.07
    Rpc
    -0.07
    Emp
    -0.07
    aan
    -0.07
    ohan
    -0.07
    otec
    -0.07
    oref
    -0.06
    POSITIVE LOGITS
    ìĭľëĭ¤
    0.07
    untr
    0.07
     ape
    0.06
    æĹ¥çĶŁ
    0.06
    ismet
    0.06
    æ¢Ń
    0.06
    atism
    0.06
    ÙĬÙĨا
    0.06
    ennale
    0.06
    æĹ¥å¤ľ
    0.06
    Activations Density 0.342%

    No Known Activations