© 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. 20395
    Prev
    Next
    INDEX
    Explanations

    admin and administration

    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
    ingly
    -0.09
    maker
    -0.08
    ledge
    -0.08
    ombine
    -0.08
    ģ
    -0.08
    mener
    -0.07
    pled
    -0.07
    leton
    -0.07
    iness
    -0.07
    dra
    -0.07
    POSITIVE LOGITS
    istrator
    0.14
    istration
    0.13
    ISTRATION
    0.10
    istra
    0.08
    ISTR
    0.08
    abbo
    0.08
     dụ
    0.08
    icus
    0.08
    ural
    0.08
    isztr
    0.08
    Activations Density 0.056%

    No Known Activations