© 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. 60848
    Prev
    Next
    INDEX
    Explanations

    density, percentage, rate, velocity, per capita

    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
    osso
    -0.10
     Sor
    -0.07
    ucu
    -0.07
    _lengths
    -0.07
    its
    -0.07
    ãģĨãģ¡ãģ«
    -0.07
    abis
    -0.07
    abora
    -0.07
     Significant
    -0.07
    Ïģιά
    -0.07
    POSITIVE LOGITS
    å¯Ĩ度
    0.10
     density
    0.09
    density
    0.08
    Density
    0.08
     densities
    0.08
    -density
    0.08
     Density
    0.07
    å¯ĨéĽĨ
    0.07
     "[%
    0.07
    å¯Ĩ
    0.07
    Activations Density 0.047%

    No Known Activations