© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

    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
    票
    -0.07
    éªļ
    -0.07
    wad
    -0.07
    æĦıè¯Ĩ
    -0.07
    ä½ķ为
    -0.06
    èĽĬ
    -0.06
    sic
    -0.06
    Declared
    -0.06
    sure
    -0.06
    uded
    -0.06
    POSITIVE LOGITS
    arie
    0.08
    iry
    0.08
    blr
    0.07
    ä¼ļæľīä¸Ģ个
    0.07
    ÙĪراÙĨ
    0.07
    sWith
    0.07
    Äģv
    0.07
    quia
    0.07
     Pens
    0.07
     Orb
    0.07
    Activations Density 0.794%

    No Known Activations