© 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. 38934
    Prev
    Next
    INDEX
    Explanations

    conditional logic

    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
    uru
    -0.07
    esu
    -0.07
    hora
    -0.07
    æĶ¾å¿ĥ
    -0.07
    å°»
    -0.07
     pru
    -0.07
     Viert
    -0.07
    åľ°åĽ¾
    -0.07
    _ERRORS
    -0.07
    kat
    -0.06
    POSITIVE LOGITS
     Teixe
    0.08
    ارÙĩ
    0.07
    é¥Ń
    0.07
    éĿŀåĩ¡
    0.07
    enerate
    0.07
    åѤ
    0.06
    .Microsoft
    0.06
    StateChanged
    0.06
     Gabrie
    0.06
     Leverkus
    0.06
    Activations Density 0.005%

    No Known Activations