© 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. 45091
    Prev
    Next
    INDEX
    Explanations

    age groups and statistics

    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
    éĢģåĩº
    -0.07
    odata
    -0.07
     newcom
    -0.07
    端åĪ°
    -0.07
    æİ¡
    -0.07
    æĪijæ°¸è¿ľ
    -0.07
    yst
    -0.07
    ensem
    -0.07
    veille
    -0.07
    vf
    -0.07
    POSITIVE LOGITS
    ÑĢак
    0.08
    å°ļåı¯
    0.08
    ä¹ĥèĩ³
    0.07
    entos
    0.07
     exc
    0.07
     moderate
    0.07
     moderately
    0.06
    ained
    0.06
    ijin
    0.06
    æıIJ请
    0.06
    Activations Density 0.193%

    No Known Activations