© 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. 62604
    Prev
    Next
    INDEX
    Explanations

    categories and specific entities

    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
     Readonly
    -0.07
    lich
    -0.07
    è¢ĸ
    -0.07
    ä¸ĢåĬ¨
    -0.07
    plates
    -0.07
    odar
    -0.07
    lass
    -0.07
    obao
    -0.06
     Prav
    -0.06
    _unused
    -0.06
    POSITIVE LOGITS
    ustos
    0.08
    å¦ĤæѤ
    0.08
    ::$
    0.07
    bral
    0.07
    auen
    0.07
    ä»İèĢĮ
    0.07
    "go
    0.07
    é³ĸ
    0.07
     thus
    0.07
    è¿ĽèĢĮ
    0.07
    Activations Density 0.015%

    No Known Activations