© 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. 57567
    Prev
    Next
    INDEX
    Explanations

    neighbourhood or local

    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
    ждÑĥ
    -0.08
    ohn
    -0.08
    è°ĭ
    -0.07
    ctal
    -0.07
     zev
    -0.07
    indra
    -0.07
     Pavilion
    -0.07
    bolt
    -0.07
     kemb
    -0.07
    acci
    -0.07
    POSITIVE LOGITS
     surrounding
    0.10
    åĽ´ç»ķ
    0.09
     around
    0.09
     okolÃŃ
    0.08
     neighborhoods
    0.08
     neighbourhood
    0.08
     вокÑĢÑĥг
    0.08
    neighbor
    0.07
     Surround
    0.07
    è¿Ļ个å°ı
    0.07
    Activations Density 0.006%

    No Known Activations