© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2983
    Prev
    Next
    INDEX
    Explanations

    software packages and commands

    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
    èĦĨå¼±çļĦ
    -0.08
     Loot
    -0.08
    auh
    -0.08
    /gpio
    -0.08
    æ°ĶçļĦ
    -0.07
    çĻ»ä¸ĬäºĨ
    -0.07
    PFN
    -0.07
     ePub
    -0.07
    èĹIJ
    -0.07
    .Tele
    -0.07
    POSITIVE LOGITS
     version
    0.08
    .exe
    0.07
    .ini
    0.07
     settings
    0.07
     Version
    0.06
     documentation
    0.06
    -built
    0.06
     Athena
    0.06
     suite
    0.06
     versions
    0.06
    Activations Density 0.274%

    No Known Activations