© 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. 41126
    Prev
    Next
    INDEX
    Explanations

    string types and names

    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
    spb
    -0.08
    asuk
    -0.08
    æĬĵå®ŀ
    -0.08
    Runner
    -0.08
    agrid
    -0.08
    ãģ©ãĤĬ
    -0.07
    æ§
    -0.07
    _cli
    -0.07
    åħ¨è¦ĨçĽĸ
    -0.07
    /framework
    -0.07
    POSITIVE LOGITS
    æ¸Ĭ
    0.07
    è¿ľå¤Ħ
    0.07
    zzi
    0.07
     environment
    0.07
    èĩªèº«
    0.06
     distant
    0.06
    æ·¡
    0.06
    éĹ¹
    0.06
     differently
    0.06
    çݯå¢ĥ
    0.06
    Activations Density 0.001%

    No Known Activations