© 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. 27908
    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
    elt
    -0.09
    adge
    -0.07
    ÑģÑĮ
    -0.07
    loader
    -0.07
    ka
    -0.07
     angkat
    -0.07
     Wenger
    -0.07
    back
    -0.07
    ich
    -0.07
    osta
    -0.07
    POSITIVE LOGITS
    uert
    0.08
    tus
    0.08
    urrences
    0.08
    uas
    0.08
    zem
    0.08
     applaud
    0.07
    usione
    0.07
    rips
    0.07
    ationToken
    0.07
    DED
    0.07
    Activations Density 0.000%

    No Known Activations