© 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. 28567
    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
    ¤
    -0.07
    kus
    -0.07
    °
    -0.06
     Cire
    -0.06
     siz
    -0.06
    éĹ´
    -0.06
    å¼¹
    -0.06
    almaz
    -0.06
     Bund
    -0.06
    zeÅĽ
    -0.06
    POSITIVE LOGITS
    orris
    0.08
    InBackground
    0.07
    itia
    0.07
    _regex
    0.07
     ('\
    0.07
    akis
    0.07
    aille
    0.07
    woods
    0.07
    ichts
    0.07
    好åIJĹ
    0.07
    Activations Density 0.000%

    No Known Activations