© 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. 32249
    Prev
    Next
    INDEX
    Explanations

    .gov

    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
    cker
    -0.07
    mun
    -0.07
    _OLD
    -0.07
    eps
    -0.07
    缨
    -0.07
     Æ¡n
    -0.07
    ferenz
    -0.06
    ived
    -0.06
    າàºĻ
    -0.06
    ban
    -0.06
    POSITIVE LOGITS
    èıģ
    0.09
    æľīæķĪæľŁèĩ³
    0.08
    èģ²
    0.08
    heet
    0.08
    ä¸ĢæľĿ
    0.07
    ãĥ³ãĤ¹
    0.07
    нови
    0.06
    à¤Ĥस
    0.06
    æıŃ
    0.06
    -progress
    0.06
    Activations Density 0.002%

    No Known Activations