© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16149
    Prev
    Next
    INDEX
    Explanations

    header files

    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
    ä¸Ģéĥİ
    -0.08
     (!((
    -0.08
    führ
    -0.07
    führt
    -0.07
    deel
    -0.07
    æl
    -0.07
    assar
    -0.07
    åIJİèĢħ
    -0.06
    .INSTANCE
    -0.06
    éĿ¡
    -0.06
    POSITIVE LOGITS
    o
    0.08
    ecc
    0.07
    лл
    0.07
    Õº
    0.07
    dom
    0.07
    op
    0.07
    _exports
    0.06
    orld
    0.06
    oppen
    0.06
    _definitions
    0.06
    Activations Density 0.489%

    No Known Activations