© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16187
    Prev
    Next
    INDEX
    Explanations

    mathematical parameters and equations

    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
    鼶鼶
    -0.07
     cry
    -0.07
     postfix
    -0.06
     restrict
    -0.06
     Noi
    -0.06
     Nile
    -0.06
    ächt
    -0.06
    ÑĩаÑģ
    -0.06
    ogr
    -0.06
     restriction
    -0.06
    POSITIVE LOGITS
     parameters
    0.08
    åĨµ
    0.08
    ocus
    0.08
    Parameters
    0.08
    chl
    0.08
    两项
    0.08
    _coeffs
    0.08
    irik
    0.08
    .parameters
    0.08
     Parameters
    0.08
    Activations Density 0.009%

    No Known Activations