© 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. 24210
    Prev
    Next
    INDEX
    Explanations

    motor neuron diseases

    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
    åIJŀåIJIJ
    -0.07
    ç³ľçĥĤ
    -0.07
    ุà¸Ķ
    -0.07
    onge
    -0.07
    aset
    -0.07
     dungeons
    -0.07
     Sanity
    -0.07
    ohl
    -0.07
    ahrt
    -0.07
    è¿Ń代
    -0.07
    POSITIVE LOGITS
    èĤĮèĤī
    0.12
     muscle
    0.12
     Muscle
    0.11
     muscles
    0.10
     tendon
    0.10
     motor
    0.10
     electrom
    0.10
     muscular
    0.09
    èĤĮ
    0.09
     ÙĦÙĬÙģ
    0.09
    Activations Density 0.126%

    No Known Activations