© 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. 8690
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    åIJīæĸ¯
    -0.08
    amn
    -0.08
    ]("
    -0.08
    unar
    -0.08
    ãĤ·ãĥ³ãĤ°
    -0.08
    æĺ¯å°ı
    -0.07
    yste
    -0.07
    кÑĢо
    -0.07
    족
    -0.07
     (:
    -0.07
    POSITIVE LOGITS
    0.08
    Å¡Äį
    0.07
     Fic
    0.07
    æ¦Ĥ念
    0.06
    åıĻ
    0.06
    éĽĦ
    0.06
    ividi
    0.06
    åĿ¤
    0.06
    ç¼ĺ
    0.06
    0.06
    Activations Density 0.005%

    No Known Activations