© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    Hz

    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
    Down
    -0.07
    ftp
    -0.07
    .addClass
    -0.06
     blast
    -0.06
    hol
    -0.06
     Gang
    -0.06
     Down
    -0.06
    åı¯æ¯Ķ
    -0.06
    ache
    -0.06
     gang
    -0.06
    POSITIVE LOGITS
    家æķĻ
    0.08
    åİŁæĺ¯
    0.08
    bear
    0.08
     Uk
    0.08
    ÐŃÐļ
    0.08
    ceria
    0.08
    .appspot
    0.07
    åŃ£åIJİ
    0.07
    æĹĭåį³
    0.07
    ogne
    0.07
    Activations Density 0.027%

    No Known Activations