© 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. 55610
    Prev
    Next
    INDEX
    Explanations

    definitions, doctrines, emotions, election, scripts

    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
    udit
    -0.08
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.08
    hind
    -0.08
    utin
    -0.08
    æľ¬æ¥¼
    -0.08
    EventData
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.07
    indu
    -0.07
    ongs
    -0.07
    abis
    -0.07
    POSITIVE LOGITS
    âĢ¦âĢ¦
    0.09
     âĢ¦
    0.08
     enlight
    0.07
     [âĢ¦]
    0.07
    æķ¢
    0.07
     [
    0.06
    urve
    0.06
    æĸĩæijĺ
    0.06
    âĢ¦
    0.06
    享
    0.06
    Activations Density 0.021%

    No Known Activations