© 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. 25967
    Prev
    Next
    INDEX
    Explanations

    .po/.mo files

    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
    estes
    -0.08
    ¨
    -0.08
    PTH
    -0.07
    ä¼ļ为
    -0.07
    erei
    -0.07
    åİŁèijĹ
    -0.07
    estas
    -0.07
    chai
    -0.07
    aeda
    -0.07
    erot
    -0.07
    POSITIVE LOGITS
    zy
    0.07
    º
    0.06
    olo
    0.06
    ®
    0.06
    æĩ¿
    0.06
    iso
    0.06
    č↵↵
    0.06
    ç´łè´¨
    0.06
    åºĶè¿IJ
    0.06
    ãĤ¹ãĥł
    0.06
    Activations Density 0.233%

    No Known Activations