© 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. 45250
    Prev
    Next
    INDEX
    Explanations

    weighted sums and averages

    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
    uris
    -0.07
    _typeof
    -0.07
    以åħįå½±åĵį
    -0.07
    icona
    -0.07
    æ¯į女
    -0.07
    kle
    -0.07
    親åŃIJ
    -0.07
    æ¶ĪåĮĸçļĦ
    -0.06
    åıĮé±¼
    -0.06
    æİĢ
    -0.06
    POSITIVE LOGITS
     weighted
    0.17
    åĬłæĿĥ
    0.15
    weighted
    0.15
     weighting
    0.13
     weights
    0.11
    æĿĥéĩį
    0.11
    weights
    0.11
     sum
    0.11
    -weight
    0.10
     sums
    0.10
    Activations Density 0.037%

    No Known Activations