© 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. 41909
    Prev
    Next
    INDEX
    Explanations

    code parsing and interpretation

    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
    ehme
    -0.07
    ierto
    -0.07
    credi
    -0.07
    inger
    -0.07
    inz
    -0.07
     Semen
    -0.07
    åįĬåĨ³èµĽ
    -0.07
    witter
    -0.06
    ersen
    -0.06
     Emplo
    -0.06
    POSITIVE LOGITS
     parsed
    0.10
     interpretation
    0.09
     interpret
    0.09
     parse
    0.08
    parsed
    0.08
    Parsed
    0.08
     interpreta
    0.08
    parse
    0.07
    解读
    0.07
     parsing
    0.07
    Activations Density 0.126%

    No Known Activations