© 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. 47221
    Prev
    Next
    INDEX
    Explanations

    timing, distance, number, duration

    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
    ParseException
    -0.09
    rast
    -0.08
    .viewmodel
    -0.08
    ulture
    -0.08
    AndView
    -0.07
    ostro
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    ẽ
    -0.07
    _icall
    -0.07
    UnitTest
    -0.07
    POSITIVE LOGITS
     length
    0.09
     number
    0.09
    number
    0.09
     duration
    0.08
     height
    0.08
     distance
    0.08
     percentage
    0.08
    次æķ°
    0.08
    éķ¿åº¦
    0.08
     radius
    0.08
    Activations Density 0.554%

    No Known Activations