© 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. 26645
    Prev
    Next
    INDEX
    Explanations

    This followed by noun or verb

    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
    вÑı
    -0.07
    éĤ£ä¹Ī容æĺĵ
    -0.07
    æīĢ以éľĢè¦ģ
    -0.07
    ism
    -0.07
    arial
    -0.07
    bor
    -0.06
    Õ¼
    -0.06
    oser
    -0.06
    ipur
    -0.06
    kant
    -0.06
    POSITIVE LOGITS
    ecker
    0.08
    yel
    0.08
    brero
    0.07
    èı²å°Ķå¾·
    0.07
    áĥĶáĥ¡
    0.07
    mener
    0.07
    /umd
    0.07
    ibaldi
    0.07
    poke
    0.07
    unders
    0.07
    Activations Density 0.004%

    No Known Activations