© 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. 7916
    Prev
    Next
    INDEX
    Explanations

    inductor (-ors, -ance, -ive)

    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
    owing
    -0.08
    adow
    -0.08
    ingue
    -0.07
    isters
    -0.07
    ynchronously
    -0.06
    pering
    -0.06
    aring
    -0.06
    nable
    -0.06
    ì¦Ī
    -0.06
    åĸ±
    -0.06
    POSITIVE LOGITS
    ãĤ¥
    0.10
    ively
    0.09
    ive
    0.09
    harma
    0.09
    eur
    0.09
    usen
    0.08
    sWith
    0.08
    erseits
    0.08
    IVE
    0.08
    iesta
    0.08
    Activations Density 0.008%

    No Known Activations