© 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. 18746
    Prev
    Next
    INDEX
    Explanations

    bin

    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
    наÑĢ
    -0.08
    åħ¨æľ¬å°ı说
    -0.07
    strate
    -0.07
    éľĦ
    -0.07
    çĭ¬åįł
    -0.06
    ted
    -0.06
    Forever
    -0.06
    zg
    -0.06
    zÄħ
    -0.06
    (OP
    -0.06
    POSITIVE LOGITS
    äum
    0.08
    à¸Ľà¸£
    0.07
     Bin
    0.07
    Bin
    0.07
    _wrapper
    0.06
    -bin
    0.06
    该æĸĩ
    0.06
    ics
    0.06
     bin
    0.06
    ibs
    0.06
    Activations Density 1.262%

    No Known Activations