© 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. 40827
    Prev
    Next
    INDEX
    Explanations

    security and risk assessment

    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
    麹
    -0.08
    enom
    -0.08
    adena
    -0.08
    ieber
    -0.07
    tabil
    -0.07
     Manz
    -0.07
     JUN
    -0.07
    HEME
    -0.07
    icch
    -0.07
    èĢĮçŁ¥
    -0.07
    POSITIVE LOGITS
     because
    0.07
    åĽłä¸ºè¿Ļ个
    0.07
    otic
    0.07
    zed
    0.07
    mes
    0.07
    大为
    0.07
    åĽłä¸ºè¿Ļ
    0.07
     azzal
    0.07
     sal
    0.07
    éĢļè¿ĩå°Ĩ
    0.07
    Activations Density 0.169%

    No Known Activations