© 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. 49132
    Prev
    Next
    INDEX
    Explanations

    substring matching

    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
    годи
    -0.08
    åįģ足çļĦ
    -0.08
    eper
    -0.07
    lendir
    -0.07
    ëĨ
    -0.07
    ablish
    -0.07
    å¦Ĥå±±
    -0.07
    ÙģÙĪ
    -0.07
    åIJĪãģĦ
    -0.07
    olley
    -0.07
    POSITIVE LOGITS
    ings
    0.09
    á»ķi
    0.07
    aneous
    0.07
    riage
    0.07
    emers
    0.07
    acent
    0.07
    Ñģой
    0.07
    etimes
    0.07
    ientos
    0.07
    iness
    0.06
    Activations Density 0.002%

    No Known Activations