© 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. 9046
    Prev
    Next
    INDEX
    Explanations

    runtime properties or setters

    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
    Ñģени
    -0.08
    èĴĤæĸ¯
    -0.07
    åĢ¾
    -0.07
    entina
    -0.07
    ãĤīãģĦ
    -0.07
    è¾±
    -0.07
    ichts
    -0.07
    _assert
    -0.07
    溺
    -0.07
     ra
    -0.07
    POSITIVE LOGITS
     currently
    0.08
    yon
    0.08
    ç»´æĮģ
    0.07
    çİ°æľīçļĦ
    0.07
    缮åīįçļĦ
    0.07
    PROP
    0.07
    verse
    0.07
    ):-
    0.07
    ionale
    0.07
    ône
    0.07
    Activations Density 0.244%

    No Known Activations