© 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. 46470
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    olo
    -0.08
    embe
    -0.07
    elson
    -0.07
    athering
    -0.06
    aliste
    -0.06
     Vit
    -0.06
    emor
    -0.06
    ucker
    -0.06
    å®ĪåĪĻ
    -0.06
    ếm
    -0.06
    POSITIVE LOGITS
    soon
    0.08
    ரா
    0.08
     primit
    0.08
    伯æģ©
    0.07
    skog
    0.07
    rix
    0.07
    _SUS
    0.07
    haj
    0.07
    nud
    0.07
     Primitive
    0.07
    Activations Density 0.015%

    No Known Activations