© 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. 21954
    Prev
    Next
    INDEX
    Explanations

    measurement units and quantities

    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
    åk
    -0.09
    é¦Ĩ
    -0.08
    ozo
    -0.08
    ead
    -0.08
    stantiate
    -0.08
    ä¸ĩåħĥ以ä¸Ĭ
    -0.07
    æľī车
    -0.07
    ä¸ĩ次
    -0.07
    usto
    -0.07
    afb
    -0.07
    POSITIVE LOGITS
     span
    0.13
    span
    0.12
     spans
    0.12
     width
    0.11
     length
    0.11
    width
    0.10
    宽度
    0.10
    跨度
    0.10
    _span
    0.10
    -span
    0.10
    Activations Density 0.017%

    No Known Activations