© 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. 25990
    Prev
    Next
    INDEX
    Explanations

    min or max value

    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
    渲
    -0.08
    ivy
    -0.07
    imo
    -0.07
    ç¼¥
    -0.07
    Multip
    -0.07
    æĢ§çĹħ
    -0.07
    ä¸Ģ缴åĿļæĮģ
    -0.07
    ebra
    -0.07
    onest
    -0.07
    lico
    -0.07
    POSITIVE LOGITS
    以åıĬ缸åħ³
    0.09
    äºĮéĥİ
    0.07
    以åıĬ
    0.07
    以åıĬä¸İ
    0.07
    åıĬåºĶçĶ¨
    0.07
    oppel
    0.06
    åıĬ使çĶ¨
    0.06
    åıĬåij¨è¾¹
    0.06
    红é¢Ĩå·¾
    0.06
    utÄĥ
    0.06
    Activations Density 0.145%

    No Known Activations