© 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. 40048
    Prev
    Next
    INDEX
    Explanations

    extract strings or data

    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
    zinho
    -0.08
    ows
    -0.08
    arity
    -0.08
    deaux
    -0.08
    estad
    -0.08
    ÑģÑĤÑĢое
    -0.08
    veau
    -0.07
    ãģ¥ãģij
    -0.07
    ople
    -0.07
    ears
    -0.07
    POSITIVE LOGITS
    aneous
    0.10
    insic
    0.09
     vẹn
    0.09
    åĴĮåŁ¹åħ»
    0.08
    OrCreate
    0.08
    ¹
    0.08
    ivism
    0.08
    IGGER
    0.08
    /release
    0.08
    inct
    0.08
    Activations Density 0.042%

    No Known Activations