© 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. 60411
    Prev
    Next
    INDEX
    Explanations

    numbers and math operations

    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
    alker
    -0.08
    strup
    -0.07
    osal
    -0.07
    ervers
    -0.07
    ваниÑİ
    -0.07
     Justi
    -0.07
    anders
    -0.07
    ylan
    -0.07
    idth
    -0.07
    åıĬåħ¶
    -0.07
    POSITIVE LOGITS
    YC
    0.08
    heet
    0.07
    boro
    0.07
     Knowing
    0.06
    GRP
    0.06
    ngu
    0.06
    ISTRA
    0.06
    drops
    0.06
    CJK
    0.06
    sett
    0.06
    Activations Density 0.001%

    No Known Activations