© 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. 60797
    Prev
    Next
    INDEX
    Explanations

    loop index i followed by <

    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
    ide
    -0.08
    æĤ¨åı¯èĥ½
    -0.07
    idou
    -0.07
    å®ĥ对
    -0.07
    æķ°ä»¥
    -0.07
    terdam
    -0.07
    è°ģæĿ¥
    -0.06
    ilde
    -0.06
    nic
    -0.06
    uki
    -0.06
    POSITIVE LOGITS
    oops
    0.08
    almaz
    0.07
    avian
    0.07
    uah
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    ogh
    0.07
    bish
    0.07
    omens
    0.07
          ↵      ↵
    0.06
    ä¸Ķä¸į
    0.06
    Activations Density 0.005%

    No Known Activations