© 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. 42288
    Prev
    Next
    INDEX
    Explanations

    documentation parameter definitions

    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
    amai
    -0.07
    ;/*
    -0.07
    çĬ¹æľªå°½
    -0.07
    λλη
    -0.07
    åľ¨ä»¥åIJİ
    -0.07
    .closest
    -0.07
    çĻ¾äºĭ
    -0.06
    rowse
    -0.06
    ä½Ļ家
    -0.06
    ster
    -0.06
    POSITIVE LOGITS
    åĸĦ
    0.07
    ãĤĪ
    0.07
    สà¸Ļ
    0.07
    /svg
    0.06
    izzling
    0.06
    iaga
    0.06
     oppure
    0.06
    aner
    0.06
    ulg
    0.06
    åĭĩå¾Ģ缴åīį
    0.06
    Activations Density 0.027%

    No Known Activations