© 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. 10437
    Prev
    Next
    INDEX
    Explanations

    in agreement with

    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
    åľ¨åĨħ
    -0.07
    عر
    -0.07
    çŀ»
    -0.07
     Stub
    -0.06
    late
    -0.06
    tại
    -0.06
    ims
    -0.06
     Anat
    -0.06
    Stub
    -0.06
     Erl
    -0.06
    POSITIVE LOGITS
     earlier
    0.10
    Earlier
    0.08
    heen
    0.08
    ubar
    0.08
     Chauff
    0.07
    åª
    0.07
    bauer
    0.07
    amal
    0.07
    adero
    0.07
    åħ¶ä»ĸ人
    0.07
    Activations Density 0.012%

    No Known Activations