© 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. 4536
    Prev
    Next
    INDEX
    Explanations

    exposed geological features

    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
    æĺ¯å¥½
    -0.08
     reassuring
    -0.08
    enqueue
    -0.08
    isson
    -0.08
     angeh
    -0.07
     Pesc
    -0.07
     xoa
    -0.07
    _GRP
    -0.07
    kli
    -0.07
    å·²ç»ıè¿ĩåİ»
    -0.07
    POSITIVE LOGITS
     revealing
    0.16
     exposing
    0.15
    æıŃ示
    0.14
     expose
    0.14
     reveal
    0.14
     exposes
    0.13
    æļ´éľ²
    0.13
     reveals
    0.13
    æıŃéľ²
    0.13
    reve
    0.13
    Activations Density 0.195%

    No Known Activations