© 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. 46213
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and special characters

    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
    èIJ±
    -0.07
    ç±³äºļ
    -0.07
    enko
    -0.07
    ene
    -0.07
    /sub
    -0.06
    acha
    -0.06
    è°Ĭ
    -0.06
    endah
    -0.06
    onex
    -0.06
    èĢ»
    -0.06
    POSITIVE LOGITS
    æĿ¥ä¹ĭ
    0.10
    atriz
    0.09
    ecten
    0.07
    ”.**
    0.07
    åħĪçĶŁåľ¨
    0.07
    ulings
    0.07
    åľ¨åĨħ
    0.07
    ãģĭãģĮ
    0.07
     htonl
    0.07
    åľ¨åĨħçļĦ
    0.07
    Activations Density 0.004%

    No Known Activations