© 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. 46170
    Prev
    Next
    INDEX
    Explanations

    fields and methods

    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
     transient
    -0.07
    æŀģåĵģ
    -0.07
    isis
    -0.06
    nap
    -0.06
    atty
    -0.06
    è£ħ车
    -0.06
    æ°¸åħ´
    -0.06
    evin
    -0.06
     ÙĪتست
    -0.06
    èĬ±èĮ¶
    -0.06
    POSITIVE LOGITS
    åĩºéĸĢ
    0.08
    ymar
    0.08
    breadcrumbs
    0.08
    èĢ¦
    0.08
    ä¿ĿæĬ¤æݪæĸ½
    0.08
    丸
    0.08
     incorpor
    0.08
    гÑĢи
    0.08
    ä½£
    0.08
    emer
    0.08
    Activations Density 0.002%

    No Known Activations