© 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. 28028
    Prev
    Next
    INDEX
    Explanations

    systematic review and analysis

    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
    ILON
    -0.08
    atoire
    -0.08
    WithPath
    -0.08
    ////////////////////////////////////////////////////////////////
    -0.08
    IGHT
    -0.08
    баланÑģи
    -0.08
    ////////////////////////////////////////////////
    -0.08
    asm
    -0.08
    åıĬ使çĶ¨
    -0.08
    éĩĺ
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.11
    -minded
    0.11
    ed
    0.09
    ALLY
    0.09
    ively
    0.09
    ãģ¦
    0.09
    æĢ§åľ°
    0.09
    åħ¥å¾®
    0.08
     minded
    0.08
    ìłģìľ¼ë¡ľ
    0.08
    Activations Density 0.011%

    No Known Activations