© 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. 18393
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     algu
    -0.08
     zet
    -0.07
    istring
    -0.07
    ickl
    -0.07
    .setdefault
    -0.07
    achter
    -0.07
    ecz
    -0.07
    icter
    -0.07
    ostr
    -0.07
    òm
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.07
    æĸ°åĬłåĿ¡
    0.07
    DataProvider
    0.06
    hek
    0.06
     beiden
    0.06
    åĺĽ
    0.06
    éĢĥ
    0.06
    è¾¾
    0.06
    _ASYNC
    0.06
    _DENIED
    0.06
    Activations Density 0.027%

    No Known Activations