© 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. 57773
    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
    ิว
    -0.08
    幸
    -0.08
    ultur
    -0.07
    egu
    -0.07
    رة
    -0.07
    ircon
    -0.07
    urr
    -0.07
    emic
    -0.07
    eki
    -0.06
    ÙĪÙĦØ©
    -0.06
    POSITIVE LOGITS
    çīĪæĿĥæīĢæľī
    0.07
    åİŁåĪĽæĸĩç«ł
    0.07
     greater
    0.07
    rias
    0.07
    åĽŀè¦Ĩ
    0.06
    Greater
    0.06
    ascal
    0.06
    antul
    0.06
    æĥĨæĢħ
    0.06
    è¢ħè¢ħ
    0.06
    Activations Density 0.000%

    No Known Activations