© 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. 20078
    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
    orna
    -0.08
    cone
    -0.07
    çļĩ
    -0.07
    梨
    -0.07
    æĪĸ以
    -0.06
    ou
    -0.06
    ifat
    -0.06
    C
    -0.06
    atern
    -0.06
    VT
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    åĴĻ
    0.08
    微信æī«çłģ
    0.08
    লà§ĩà¦ĸ
    0.08
     Ilmais
    0.08
    _FILENO
    0.08
     Gis
    0.08
    ngine
    0.07
    itante
    0.07
    imizer
    0.07
    Activations Density 0.000%

    No Known Activations