© 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. 50284
    Prev
    Next
    INDEX
    Explanations

    space

    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
    zelf
    -0.09
    shan
    -0.08
    ä¸įè¡°
    -0.08
    меÑĤи
    -0.08
    ìĤ¬íķŃ
    -0.08
    essen
    -0.07
    atively
    -0.07
     бÑĭ
    -0.07
     sekali
    -0.07
    elson
    -0.07
    POSITIVE LOGITS
    ful
    0.09
    lessly
    0.09
    ways
    0.09
    belt
    0.08
    holder
    0.08
    åĨħçļĦ
    0.08
    -temp
    0.08
    keeping
    0.08
    -saving
    0.08
    walker
    0.08
    Activations Density 0.053%

    No Known Activations