© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17462
    Prev
    Next
    INDEX
    Explanations

    citations and DOIs

    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
    ë¦ī
    -0.08
     handl
    -0.08
    edList
    -0.08
    dings
    -0.08
    ÄĽÅ¾
    -0.08
    ضر
    -0.08
     goog
    -0.07
    _oauth
    -0.07
    ÃĤM
    -0.07
    eger
    -0.07
    POSITIVE LOGITS
    å¥Ķèµ°
    0.06
    è«
    0.06
    ahlen
    0.06
    _callable
    0.06
    =sys
    0.06
    kaar
    0.06
    anco
    0.06
     internal
    0.06
    çİĭä¿Ĭ
    0.06
    jsp
    0.06
    Activations Density 0.110%

    No Known Activations