© 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. 55419
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    isie
    -0.07
    arie
    -0.07
     Attr
    -0.07
    åIJįå±±
    -0.07
    .defaultProps
    -0.07
    TextNode
    -0.06
    utsch
    -0.06
    ê¶ĮìĿ´
    -0.06
    agan
    -0.06
    åIJ¸å¼ķ
    -0.06
    POSITIVE LOGITS
    VOID
    0.07
    umpl
    0.07
    ampion
    0.07
     bá»ķng
    0.07
    onso
    0.07
    urations
    0.07
    jenigen
    0.07
    ÐĶÐIJÐł
    0.07
    اÙĥÙħ
    0.07
    akedown
    0.07
    Activations Density 0.000%

    No Known Activations