© 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. 24778
    Prev
    Next
    INDEX
    Explanations

    section or reference markers

    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
    á»ģ
    -0.07
    itage
    -0.07
    orno
    -0.07
    osu
    -0.07
    çĸ±
    -0.07
    ilha
    -0.06
     ?:
    -0.06
    io
    -0.06
    fr
    -0.06
    edor
    -0.06
    POSITIVE LOGITS
    į°
    0.08
    ">*</
    0.08
    миÑı
    0.07
    عÙĦÙħ
    0.07
    |"
    0.07
    IGIN
    0.07
    añ
    0.07
    âĸ¼
    0.06
    trak
    0.06
    |int
    0.06
    Activations Density 0.184%

    No Known Activations