© 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. 32491
    Prev
    Next
    INDEX
    Explanations

    date and time

    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
    ëıħ
    -0.08
    aca
    -0.08
    綺
    -0.08
    prot
    -0.08
    onya
    -0.07
    ney
    -0.07
    æ±Łè·¯
    -0.07
    ä¿
    -0.07
    leb
    -0.07
    å«ī
    -0.07
    POSITIVE LOGITS
    .templates
    0.07
    umes
    0.07
     Benchmark
    0.06
     Enumerator
    0.06
    aliza
    0.06
    dade
    0.06
    _mgr
    0.06
    éĩijèĬ±
    0.06
    .kwargs
    0.06
    بÙĪر
    0.06
    Activations Density 0.112%

    No Known Activations