© 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. 15797
    Prev
    Next
    INDEX
    Explanations

    compactness and lightness

    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
    çķħéĢļ
    -0.07
    inos
    -0.06
     stead
    -0.06
    ZZ
    -0.06
    cope
    -0.06
     smoothed
    -0.06
    æĢ§è´¨çļĦ
    -0.06
    _lang
    -0.06
    apura
    -0.06
    é»ĺ
    -0.06
    POSITIVE LOGITS
    ç´§åĩij
    0.13
    compact
    0.12
     compact
    0.11
    Compact
    0.11
     Compact
    0.10
     kompak
    0.10
     компак
    0.10
    éĩįéĩıè½»
    0.10
    éĩįéĩı
    0.10
    åįłåľ°
    0.09
    Activations Density 0.365%

    No Known Activations