© 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. 58310
    Prev
    Next
    INDEX
    Explanations

    vim, how, can

    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
    å¾Ģ常ä¸Ģæł·
    -0.10
    ellaneous
    -0.10
     ä»ĬæĹ¥
    -0.10
    ousel
    -0.09
    ESTA
    -0.09
    äºĨä¸ŃåĽ½
    -0.09
    çļĦéĤ£ä¸ª
    -0.09
    翼翼
    -0.09
    dbl
    -0.09
    ï¼ĮãĢĬ
    -0.09
    POSITIVE LOGITS
    (
    0.10
    -
    0.10
    *
    0.09
    åħ¶
    0.09
    _
    0.09
    åľ¨
    0.09
    u
    0.09
    ëį°
    0.09
    Ùĩ
    0.09
    \
    0.08
    Activations Density 0.007%

    No Known Activations