© 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. 2359
    Prev
    Next
    INDEX
    Explanations

    distance measurement or calculation

    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
    schen
    -0.09
    Neal
    -0.08
    usterity
    -0.08
    ishly
    -0.08
    élix
    -0.08
    kada
    -0.08
    éĹ´çĽĺçªģåĩº
    -0.08
    олÑĮ
    -0.08
    scher
    -0.08
    thal
    -0.07
    POSITIVE LOGITS
    ä¸ĭä¸Ģ级è¿ĺéľĢ
    0.08
    /time
    0.08
    ing
    0.08
    ances
    0.08
    ientes
    0.08
    а
    0.07
    ftime
    0.07
    leep
    0.07
     traveled
    0.07
    kolwiek
    0.07
    Activations Density 0.023%

    No Known Activations