© 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. 42877
    Prev
    Next
    INDEX
    Explanations

    bone, mechanical, mental, vascular, cardiac dysfunction

    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
    pite
    -0.06
     cuadr
    -0.06
     ne
    -0.06
    _checks
    -0.06
    жд
    -0.06
    çħĮ
    -0.06
    zÃŃ
    -0.06
     vers
    -0.06
    aler
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    贯穿äºİ
    0.09
    缸åħ³æݨèįIJ
    0.08
    enus
    0.08
    ibar
    0.07
    -conscious
    0.07
    миÑĢа
    0.07
    è¿ĻäºĭåĦ¿
    0.07
    avra
    0.07
    å¼Ģ课
    0.07
    _handling
    0.07
    Activations Density 0.996%

    No Known Activations