© 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. 61560
    Prev
    Next
    INDEX
    Explanations

    data types and variables

    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
     withObject
    -0.08
    微信åIJĮåı·
    -0.08
    <&
    -0.07
    kens
    -0.07
    _',
    -0.07
    åį´ä¹Ł
    -0.07
    /loading
    -0.07
    Ñģел
    -0.07
    endon
    -0.07
    dach
    -0.07
    POSITIVE LOGITS
    L
    0.07
    gr
    0.07
    [][]
    0.07
    临
    0.07
    CPP
    0.06
     gr
    0.06
    гÑĢада
    0.06
     den
    0.06
    3
    0.06
    ier
    0.06
    Activations Density 0.126%

    No Known Activations