© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    properties of

    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
    ividual
    -0.09
    ĻĤ
    -0.08
    inear
    -0.08
    ä¸įåı¯æĢķ
    -0.08
     Aufwand
    -0.07
    enin
    -0.07
    ÚĨار
    -0.07
    iglia
    -0.07
    isure
    -0.07
     comprend
    -0.07
    POSITIVE LOGITS
     properties
    0.12
     Properties
    0.11
     property
    0.10
    -property
    0.10
     Property
    0.09
    property
    0.09
     characteristics
    0.09
    çī¹æĢ§
    0.09
    properties
    0.09
    Property
    0.08
    Activations Density 0.024%

    No Known Activations