© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54990
    Prev
    Next
    INDEX
    Explanations

    constituted by / constitutes

    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
    Negative Logits
    WARDS
    -0.09
    yer
    -0.08
    rens
    -0.07
    ä¹İä¹İçļĦ
    -0.07
    次çļĦ
    -0.07
    es
    -0.07
    aukee
    -0.07
    Äģk
    -0.06
    usband
    -0.06
    cape
    -0.06
    POSITIVE LOGITS
    ively
    0.10
    è¦ģ件
    0.09
    ainers
    0.09
    igli
    0.08
    rost
    0.08
    OfSize
    0.08
    OrUpdate
    0.08
    enhagen
    0.08
    InChildren
    0.08
    itional
    0.08
    Activations Density 0.013%

    No Known Activations