© 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. 12255
    Prev
    Next
    INDEX
    Explanations

    west, higher, age, ft

    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
    chie
    -0.08
    çĽ
    -0.08
    avan
    -0.07
    ula
    -0.07
    ocket
    -0.06
    åĻ¢
    -0.06
    thing
    -0.06
    èľĢ
    -0.06
    ewire
    -0.06
    inta
    -0.06
    POSITIVE LOGITS
    å¾·åŁº
    0.09
    ameda
    0.08
    adak
    0.07
    arris
    0.07
    urts
    0.07
    -Smith
    0.07
    足ä¸įåĩº
    0.07
     Verd
    0.07
    enville
    0.07
    rapper
    0.07
    Activations Density 0.049%

    No Known Activations