© 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. 32919
    Prev
    Next
    INDEX
    Explanations

    Introduction sections

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ulong
    -0.06
    auta
    -0.06
    åģļ为
    -0.06
    пÑĢÑĭ
    -0.06
    åħ¬å®³
    -0.06
    ãģŁãģ¨
    -0.06
    çĶ¨è½¦
    -0.06
    åĩı
    -0.06
    åı¯äº²
    -0.06
    POSITIVE LOGITS
    razi
    0.08
    udge
    0.08
    meg
    0.07
    KeySpec
    0.07
    icket
    0.07
    ัà¸Ķ
    0.07
    èIJ¨æĸ¯
    0.07
    بÙĬØ©
    0.07
     Accessed
    0.07
    并åIJĮæŶ
    0.07
    Activations Density 0.099%

    No Known Activations