© 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. 55586
    Prev
    Next
    INDEX
    Explanations

    set context or parameters

    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
    erweise
    -0.11
    erii
    -0.09
    entifier
    -0.08
    erken
    -0.08
    keit
    -0.08
    erce
    -0.08
    ä¸ĸ家
    -0.08
    idade
    -0.08
    ász
    -0.08
    erende
    -0.08
    POSITIVE LOGITS
    tlement
    0.18
    tle
    0.13
    ters
    0.10
    uptools
    0.10
    ings
    0.10
    ÑĩаÑģ
    0.10
    ewart
    0.10
    sockopt
    0.10
    TING
    0.09
    istical
    0.09
    Activations Density 0.128%

    No Known Activations