© 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. 38440
    Prev
    Next
    INDEX
    Explanations

    Modern Living

    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
    ä¸īå°º
    -0.08
    ARIANT
    -0.08
    oku
    -0.07
    vented
    -0.07
    ientos
    -0.07
    sehen
    -0.07
    èļª
    -0.07
    기íļį
    -0.07
    caster
    -0.07
    çī¹æĸ¯
    -0.07
    POSITIVE LOGITS
    åįģ个
    0.08
    åįģ
    0.08
    åįģåħ¨
    0.07
    bag
    0.07
     Downing
    0.07
     ten
    0.07
    èıĬ
    0.07
    第åįģ
    0.07
     Ten
    0.06
    apers
    0.06
    Activations Density 0.243%

    No Known Activations