© 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. 48212
    Prev
    Next
    INDEX
    Explanations

    This is / the noun

    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
    mps
    -0.07
    ogn
    -0.07
    ombo
    -0.07
    lle
    -0.06
    å°Ĩæľī
    -0.06
     oy
    -0.06
    ldr
    -0.06
    æıIJèµ·
    -0.06
    lu
    -0.06
    inite
    -0.06
    POSITIVE LOGITS
    å·´åħĭ
    0.08
    ä¸ī楼
    0.07
    å·®çļĦ
    0.07
    aturi
    0.07
    à¦¿à¦ľ
    0.07
    å·®
    0.07
    plied
    0.07
    è¡Įä¹ĭ
    0.07
    ?id
    0.07
    spir
    0.07
    Activations Density 0.001%

    No Known Activations