© 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. 18218
    Prev
    Next
    INDEX
    Explanations

    lean body, Six Sigma, methodology, billing

    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
    ypse
    -0.08
    ity
    -0.08
     Ñģобой
    -0.07
    iseur
    -0.07
    redo
    -0.07
    端åĢª
    -0.07
    æ¶Łæ¼ª
    -0.07
    ion
    -0.07
    iglio
    -0.06
    ¥
    -0.06
    POSITIVE LOGITS
    ciano
    0.09
    jenigen
    0.08
    lah
    0.08
    (li
    0.08
    κÏĮ
    0.08
    tron
    0.08
    çīĪ
    0.08
    imately
    0.08
    iverse
    0.07
    labs
    0.07
    Activations Density 0.001%

    No Known Activations