© 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. 1281
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions $\frac{a}{b}$

    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
    mert
    -0.07
    ////////////////////////////////////////////////////////////////
    -0.07
    onda
    -0.07
    ηÏĥη
    -0.06
    angkan
    -0.06
    ÙĪÙĨد
    -0.06
    ifte
    -0.06
    vÄĽ
    -0.06
    æľ¬ç«ĻæīĢæľī
    -0.06
    urts
    -0.06
    POSITIVE LOGITS
    hurst
    0.09
    ady
    0.09
     @}
    0.09
    oriously
    0.08
     siquiera
    0.08
    forth
    0.08
    å°Ķ
    0.08
    theless
    0.07
    ousel
    0.07
    Å¡Äį
    0.07
    Activations Density 0.004%

    No Known Activations