© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    predictive modeling

    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
    kus
    -0.08
     contraint
    -0.08
    _overlap
    -0.08
    kota
    -0.08
     Boyd
    -0.08
    illons
    -0.08
    .constraint
    -0.07
    uels
    -0.07
    umer
    -0.07
    @student
    -0.07
    POSITIVE LOGITS
     partial
    0.08
    partial
    0.07
     terdekat
    0.07
     closest
    0.07
     nearest
    0.07
    oldt
    0.06
     subtract
    0.06
    æĹłå¸¸
    0.06
     nearby
    0.06
     extracted
    0.06
    Activations Density 0.017%

    No Known Activations