© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    minutes after or from replacement

    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
    天å®ī
    -0.08
    çĽĹ
    -0.07
    éħİ
    -0.07
    ìıŁ
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.07
    pen
    -0.07
    imetype
    -0.07
    ìĦ±ê¸ī
    -0.07
    unday
    -0.07
    _pat
    -0.07
    POSITIVE LOGITS
    agas
    0.07
    onta
    0.07
    IID
    0.06
    à¸Ļà¸ķà¹Į
    0.06
    orio
    0.06
    arate
    0.06
    ast
    0.06
    oll
    0.06
    _EXIT
    0.06
    çĿĢéĩį
    0.06
    Activations Density 0.138%

    No Known Activations