© 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. 43481
    Prev
    Next
    INDEX
    Explanations

    properties or qualities

    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
    anzi
    -0.09
    çī¹æĸ°
    -0.08
    TEMPLATE
    -0.08
     اÙĦباÙĦ
    -0.08
    åIJįæĢĿ
    -0.08
    mise
    -0.08
    andom
    -0.08
    èĢĮå·²
    -0.07
    wers
    -0.07
    _separator
    -0.07
    POSITIVE LOGITS
    ç³»æķ°
    0.10
    -related
    0.09
     coefficient
    0.08
    æĮĩæķ°
    0.08
    ç¨ĭ度
    0.08
     expressed
    0.08
    normalized
    0.08
    主è¦ģä½ĵçİ°åľ¨
    0.08
     index
    0.08
     represented
    0.08
    Activations Density 0.326%

    No Known Activations