© 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. 26691
    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
    atika
    -0.07
    atge
    -0.07
    oyal
    -0.07
    anal
    -0.07
     Commission
    -0.07
    allis
    -0.06
    anja
    -0.06
    .props
    -0.06
     sucker
    -0.06
    ampire
    -0.06
    POSITIVE LOGITS
    Submitted
    0.07
    loch
    0.07
    ضة
    0.07
    .substr
    0.07
    oner
    0.07
    ennom
    0.07
    ometown
    0.07
    Ши
    0.07
    .lib
    0.06
    orts
    0.06
    Activations Density 0.000%

    No Known Activations