© 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. 30721
    Prev
    Next
    INDEX
    Explanations

    states and actions

    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
     Kand
    -0.07
    为己
    -0.07
    رÙģ
    -0.07
     Tener
    -0.07
    æĤį
    -0.07
     Mén
    -0.07
    ram
    -0.06
    rong
    -0.06
    -fl
    -0.06
     Jambi
    -0.06
    POSITIVE LOGITS
    azin
    0.08
    ornings
    0.07
    izard
    0.07
    驱
    0.07
    zos
    0.07
    imson
    0.07
     Zut
    0.07
    æĸ¯åħĭ
    0.07
    åı¯ä»¥èĩªçĶ±
    0.07
    ä¸Ĭå½ĵ
    0.07
    Activations Density 0.045%

    No Known Activations