© 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. 34455
    Prev
    Next
    INDEX
    Explanations

    tokens following `c`

    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
    æĢĿ
    -0.07
    ahr
    -0.06
    LAND
    -0.06
    лек
    -0.06
    éĿŀ常å¤ļçļĦ
    -0.06
     Daddy
    -0.06
    èĩª
    -0.06
    zelf
    -0.06
    ż
    -0.06
    UAL
    -0.06
    POSITIVE LOGITS
    crement
    0.07
    lm
    0.07
    Ñĩений
    0.07
    äºĶæĿ¡
    0.07
    åĪ©çī©
    0.07
    çĶ»åĩº
    0.07
    itzen
    0.07
     insta
    0.07
    æĬĬåŃ¦ä¹ł
    0.07
    WithString
    0.07
    Activations Density 0.002%

    No Known Activations