© 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. 57679
    Prev
    Next
    INDEX
    Explanations

    medical center

    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
     hollow
    -0.07
    èŁ
    -0.07
    arters
    -0.07
    _modifier
    -0.07
    fav
    -0.07
    chn
    -0.06
    UCE
    -0.06
    é«ĺéĢŁä¸ĭè½½
    -0.06
    uce
    -0.06
    ondre
    -0.06
    POSITIVE LOGITS
    olley
    0.09
    _unused
    0.08
    .fi
    0.08
    ippo
    0.08
    åħ³èĬĤ
    0.08
    ä¸ĵ
    0.08
    æĬµ
    0.08
    鸳
    0.07
    .unlink
    0.07
     Chron
    0.07
    Activations Density 0.002%

    No Known Activations