© 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. 47683
    Prev
    Next
    INDEX
    Explanations

    elliptical shapes and ovals

    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
    gement
    -0.08
    aket
    -0.08
    /response
    -0.08
    leine
    -0.08
    enance
    -0.08
    ukt
    -0.08
    leman
    -0.07
    åıĬéĶĢåĶ®
    -0.07
    æ·ĭæ¼ĵ
    -0.07
    _DEFINED
    -0.07
    POSITIVE LOGITS
    å½¢çļĦ
    0.11
    ipse
    0.09
    -shaped
    0.09
    å½¢
    0.08
    vorm
    0.08
    ation
    0.07
    -like
    0.07
    äre
    0.07
    idium
    0.07
    æł·çļĦ
    0.07
    Activations Density 0.007%

    No Known Activations