© 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. 48285
    Prev
    Next
    INDEX
    Explanations

    width of

    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
    ../
    -0.08
    ebes
    -0.08
     módon
    -0.08
    ียà¹Į
    -0.07
    Produc
    -0.07
     viá»ĩc
    -0.07
    unes
    -0.07
    меÑĤи
    -0.07
    ivec
    -0.07
    ead
    -0.07
    POSITIVE LOGITS
    iness
    0.10
    ened
    0.10
    cana
    0.08
    -ranging
    0.08
    ening
    0.08
    czeÅĽ
    0.08
    =device
    0.07
    pread
    0.07
    szyscy
    0.07
    less
    0.07
    Activations Density 0.036%

    No Known Activations