© 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. 46916
    Prev
    Next
    INDEX
    Explanations

    announced result diagnosis

    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
    irk
    -0.07
    è¹Ħ
    -0.07
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
     excerpts
    -0.06
    åįĬ
    -0.06
    CONT
    -0.06
    enstein
    -0.06
    ëŁ½
    -0.06
    поÑĢÑĤа
    -0.06
    obe
    -0.06
    POSITIVE LOGITS
    以åıĬ缸åħ³
    0.08
     kèm
    0.08
    stav
    0.07
     disertai
    0.07
    andest
    0.07
    éĿĴ天
    0.07
    请åijĬçŁ¥
    0.07
    bou
    0.07
    以åıĬ对
    0.07
    ieti
    0.07
    Activations Density 0.003%

    No Known Activations