© 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. 21269
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
    è¹
    -0.07
    wur
    -0.07
    tez
    -0.07
    endale
    -0.07
    稿件æĿ¥æºIJ
    -0.07
    είÏĦε
    -0.07
    lehr
    -0.06
    åįĬ
    -0.06
    å¾Ĵ
    -0.06
     sever
    -0.06
    POSITIVE LOGITS
    ány
    0.08
     refus
    0.07
    alus
    0.07
    åħ¬å¹³çļĦ
    0.07
    /address
    0.07
    çļĦåİŁåĪĻ
    0.07
    Ñĩин
    0.07
     Us
    0.07
    iento
    0.07
    åĩºä¼ļ
    0.07
    Activations Density 0.033%

    No Known Activations