© 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. 23028
    Prev
    Next
    INDEX
    Explanations

    code structures with č

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ÏĢή
    -0.06
    atore
    -0.06
    ¶
    -0.06
    èªĩ
    -0.06
    골
    -0.06
     overst
    -0.06
    家乡
    -0.06
    .mongodb
    -0.06
    _cpus
    -0.06
    POSITIVE LOGITS
    lys
    0.08
    flater
    0.08
    locate
    0.08
    rink
    0.08
    rapper
    0.08
    ĤŃ
    0.08
     Feliz
    0.08
    ocol
    0.07
    ments
    0.07
    inker
    0.07
    Activations Density 0.001%

    No Known Activations