© 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. 48411
    Prev
    Next
    INDEX
    Explanations

    local sense, chart, dif

    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
     knowingly
    -0.08
    ipas
    -0.07
    ired
    -0.07
    River
    -0.07
     Tories
    -0.07
    iche
    -0.07
    èĢģå°ij
    -0.07
    åľ¨åħĪ
    -0.07
    å¡«
    -0.07
    .addValue
    -0.07
    POSITIVE LOGITS
    å±Ģéĥ¨çļĦ
    0.10
    å±Ģéĥ¨
    0.10
    local
    0.09
     locally
    0.09
    _LOCAL
    0.09
    (local
    0.09
     Local
    0.09
     local
    0.09
    (Local
    0.09
    near
    0.09
    Activations Density 0.004%

    No Known Activations