© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39471
    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
     solid
    -0.08
    solid
    -0.08
    odore
    -0.07
     pasto
    -0.07
    å½ĵéĿ¢
    -0.07
    ustom
    -0.07
    ival
    -0.07
    Solid
    -0.07
    amus
    -0.07
    åĽº
    -0.07
    POSITIVE LOGITS
    mares
    0.07
    jÃŃ
    0.07
    parated
    0.06
     ÏĢάν
    0.06
     ...
    0.06
    æŁIJæŁIJ
    0.06
    WithType
    0.06
    nell
    0.06
    ä¹İ
    0.06
     xá
    0.06
    Activations Density 0.000%

    No Known Activations