© 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. 39645
    Prev
    Next
    INDEX
    Explanations

    arithmetic 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
    elsen
    -0.08
    马è¹Ħ
    -0.07
    uss
    -0.07
    箫
    -0.07
    _LINUX
    -0.07
    Mark
    -0.06
    assel
    -0.06
     Marque
    -0.06
    itze
    -0.06
    asant
    -0.06
    POSITIVE LOGITS
    %f
    0.08
    对人çļĦ
    0.07
    大河
    0.07
    -INF
    0.07
    lom
    0.07
    ciano
    0.07
    greens
    0.07
     GroÃŁ
    0.07
    ichert
    0.07
    vement
    0.07
    Activations Density 0.276%

    No Known Activations