© 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. 58102
    Prev
    Next
    INDEX
    Explanations

    particularly teenagers

    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
    æºħ
    -0.07
    loyd
    -0.07
    ç»Ī
    -0.06
    æı½
    -0.06
    agoon
    -0.06
    çļĦæŶåĢĻäºĨ
    -0.06
    istro
    -0.06
    äºĨè¿Ļ个
    -0.06
    达产年
    -0.06
    .onError
    -0.06
    POSITIVE LOGITS
     обаÑĩе
    0.09
    ä¹ĭæīĢ以
    0.07
    rez
    0.07
    иÑģка
    0.07
     EITHER
    0.07
    éĿĻçļĦ
    0.07
     zwar
    0.07
    ÙijØ©
    0.07
    uges
    0.07
    çķĮ
    0.07
    Activations Density 1.324%

    No Known Activations