© 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. 34461
    Prev
    Next
    INDEX
    Explanations

    'Bill', 'pizza', 'UK'

    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
    awa
    -0.07
    åľ¨è¿Ļç§į
    -0.07
    avanaugh
    -0.07
     Stein
    -0.06
    导
    -0.06
    èĬĿ
    -0.06
    kin
    -0.06
    uru
    -0.06
    åŃľ
    -0.06
    atten
    -0.06
    POSITIVE LOGITS
    mers
    0.08
    ÑĦаÑĢ
    0.07
    åıĺæĽ´è®°å½ķ
    0.07
     compac
    0.07
    oningen
    0.07
    asilan
    0.07
    rede
    0.07
    -Star
    0.07
    umpang
    0.07
     AssemblyVersion
    0.07
    Activations Density 0.453%

    No Known Activations