© 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. 19653
    Prev
    Next
    INDEX
    Explanations

    document closing brace

    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
    [href
    -0.07
    enius
    -0.07
    åħ¥ãĤĬ
    -0.06
    èĩªæĿ¥
    -0.06
    quem
    -0.06
    ارد
    -0.06
    enaar
    -0.06
    äºĮèĢħ
    -0.06
     Ec
    -0.06
    åĩ«
    -0.06
    POSITIVE LOGITS
    河山
    0.07
    izr
    0.07
    resco
    0.07
    iface
    0.07
    ä¿IJ
    0.06
    bbing
    0.06
    rotate
    0.06
    为ä»Ģä¹Ī说
    0.06
     ifndef
    0.06
    нно
    0.06
    Activations Density 0.017%

    No Known Activations