© 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. 51384
    Prev
    Next
    INDEX
    Explanations

    software features and usage

    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
    èĢĮéĻį
    -0.09
    addock
    -0.08
    æīĢæľª
    -0.08
    ardy
    -0.07
    .mozilla
    -0.07
    æĸ°çIJĨ念
    -0.07
    kers
    -0.07
    åįĥ
    -0.07
    itano
    -0.07
    ACKET
    -0.07
    POSITIVE LOGITS
    à¹ĥà¸Ĭà¹īà¸ĩาà¸Ļ
    0.07
    使çĶ¨æŶ
    0.07
    ABS
    0.07
     Alexander
    0.06
    éĺħ
    0.06
    SAN
    0.06
    åı°ä¸ĭ
    0.06
    使çĶ¨æĸ¹æ³ķ
    0.06
    æĬķåħ¥ä½¿çĶ¨
    0.06
    enu
    0.06
    Activations Density 0.704%

    No Known Activations