© 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. 56122
    Prev
    Next
    INDEX
    Explanations

    parts of objects

    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
    zzo
    -0.07
    -strokes
    -0.07
    äºĮè¿ŀ
    -0.07
    æĹłéĹ»
    -0.07
    ìĺ¤ëĭĪ
    -0.07
    lassen
    -0.06
    λÏįÏĦε
    -0.06
    å¼łé£ŀ
    -0.06
    èĻ«çĹħ
    -0.06
    Lgs
    -0.06
    POSITIVE LOGITS
     bersangkutan
    0.09
    ulet
    0.08
     ÙĪبÙĬÙĨ
    0.08
     itself
    0.07
    uerto
    0.07
    iece
    0.07
    ÛķÚ©
    0.07
    é¢ľ
    0.07
    CTRL
    0.07
    æľ¬èº«çļĦ
    0.07
    Activations Density 0.104%

    No Known Activations