© 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. 41788
    Prev
    Next
    INDEX
    Explanations

    object keys and definitions

    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
    afil
    -0.08
    ç¼Ī
    -0.08
    .CompareTo
    -0.07
    èĢĮä»Ĭ
    -0.07
    /pi
    -0.07
     Erw
    -0.07
    оÑģÑĥ
    -0.07
    次æµıè§Ī
    -0.07
    æĿ¡è¯Ħä»·
    -0.07
    è¿Ļæł¹
    -0.07
    POSITIVE LOGITS
    .keys
    0.11
    keys
    0.11
     keys
    0.11
    .Keys
    0.10
    Keys
    0.09
     Keys
    0.08
    _keys
    0.08
    -keys
    0.08
     Dictionary
    0.08
    éĶ®
    0.08
    Activations Density 0.296%

    No Known Activations