© 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. 15595
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
    åij
    -0.06
    并没æľī
    -0.06
    éĻ¤äºĨ
    -0.06
    éĻ¤
    -0.06
    ache
    -0.06
     شع
    -0.06
    old
    -0.06
    _syntax
    -0.06
    满
    -0.06
    ¨
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.11
    ois
    0.08
     بعدÙĩ
    0.08
    -animate
    0.08
    ulong
    0.08
    èĢģé¼ł
    0.08
    çļĦåı«
    0.08
     vice
    0.08
    .Sprintf
    0.08
    .NewReader
    0.08
    Activations Density 0.072%

    No Known Activations