© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4585
    Prev
    Next
    INDEX
    Explanations

    servants, assistants, guards, pages

    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
    bele
    -0.07
    ász
    -0.07
    lant
    -0.07
    akor
    -0.07
    validators
    -0.07
    plib
    -0.06
     raging
    -0.06
    éro
    -0.06
     Ñĥдо
    -0.06
    å¯¼åĽ¾
    -0.06
    POSITIVE LOGITS
    å¿łå¿ĥ
    0.11
     setia
    0.10
    å¿łè¯ļ
    0.10
    åĬŀäºĭ
    0.10
    åįıåĬ©
    0.09
     servants
    0.09
    伺åĢĻ
    0.09
     obsÅĤugi
    0.09
     loyal
    0.09
    serv
    0.09
    Activations Density 0.267%

    No Known Activations