© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    group policies

    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
    uskan
    -0.08
    opak
    -0.07
    amax
    -0.07
    éľĢè¦ģæıIJä¾Ľ
    -0.07
    äºİè¡Į
    -0.07
    ail
    -0.07
    zan
    -0.07
    ziu
    -0.07
    *width
    -0.07
    gnore
    -0.07
    POSITIVE LOGITS
    æĺ
    0.08
    æľ¬èº«
    0.07
    erca
    0.07
     itself
    0.07
    ä¹ħèĢĮ
    0.06
    æł
    0.06
    anners
    0.06
    Revision
    0.06
    sse
    0.06
    éĥ¨
    0.06
    Activations Density 0.011%

    No Known Activations