© 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. 44103
    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
    adden
    -0.08
    ingos
    -0.08
    æĢ¥
    -0.07
    æľ¬èº«
    -0.07
    UGC
    -0.07
    usa
    -0.07
    åıĬ产åĵģ
    -0.07
    å¨ĩ
    -0.07
    oft
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
    POSITIVE LOGITS
    itaire
    0.07
    unan
    0.07
     noop
    0.07
    reland
    0.06
     Infra
    0.06
    WithValue
    0.06
     Dial
    0.06
    achim
    0.06
    ervers
    0.06
    询价
    0.06
    Activations Density 0.000%

    No Known Activations