© 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. 38613
    Prev
    Next
    INDEX
    Explanations

    Answer comments

    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
    _PROTOCOL
    -0.07
    zzi
    -0.07
    æĢ»ä½ĵä¸Ĭ
    -0.06
     ifndef
    -0.06
     occupied
    -0.06
     noqa
    -0.06
     unofficial
    -0.06
     inhabit
    -0.06
    åijĨ
    -0.06
    å¿Ļ
    -0.06
    POSITIVE LOGITS
    ouver
    0.08
    ç¥ŀçİĭ
    0.07
    forge
    0.07
    Needed
    0.07
    roller
    0.07
    ovn
    0.07
    intl
    0.07
    ledge
    0.07
    æĪIJåĬŁåIJİåį³åı¯
    0.07
    ov
    0.07
    Activations Density 0.008%

    No Known Activations