© 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. 38283
    Prev
    Next
    INDEX
    Explanations

    entire function, growth, Stein, continuity

    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
    deo
    -0.08
    Ñĩо
    -0.07
     кваÑĢÑĤал
    -0.07
    å±ħæĺĵ
    -0.07
    åĭ¿æī°
    -0.07
    æįı
    -0.07
    ï¸İ
    -0.07
    bay
    -0.07
    åIJĪåIJĮæŶ
    -0.07
     demonstr
    -0.07
    POSITIVE LOGITS
     growth
    0.08
    _growth
    0.08
    growth
    0.07
    rowth
    0.07
    iah
    0.07
    天马
    0.07
     zar
    0.07
    ihn
    0.07
     ÙĨÙħÙĪ
    0.07
    ä¸Ģåį·
    0.07
    Activations Density 0.010%

    No Known Activations