© 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. 22914
    Prev
    Next
    INDEX
    Explanations

    limits involving infinity

    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
    åħĭåĬĽ
    -0.09
    dorf
    -0.07
    åĨĴçĿĢ
    -0.07
    fs
    -0.07
     intra
    -0.07
    amel
    -0.07
    çĻ½çĻ½
    -0.07
    çļĦ第ä¸Ģ天
    -0.07
    è¾Ľäº¥
    -0.07
    çģ«çĤī
    -0.07
    POSITIVE LOGITS
     distant
    0.08
    ezo
    0.07
    è¿ľå¤Ħ
    0.07
     дале
    0.07
     Scarborough
    0.07
     behaviour
    0.07
     asympt
    0.07
    é£İè½»
    0.07
     behavior
    0.07
     sparse
    0.07
    Activations Density 0.012%

    No Known Activations