© 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. 33592
    Prev
    Next
    INDEX
    Explanations

    code blocks with delimiters

    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
    GO
    -0.07
     instead
    -0.07
    ht
    -0.06
    Eu
    -0.06
    go
    -0.06
    arty
    -0.06
    Run
    -0.06
     GO
    -0.06
    çĶŁè®¡
    -0.06
    è«ı
    -0.06
    POSITIVE LOGITS
    resco
    0.11
    丽èİİ
    0.08
    Mapping
    0.08
    æ¥Ĥ
    0.07
    ornment
    0.07
    retti
    0.07
    suma
    0.07
    ompiler
    0.07
    大åŃ¦æľ¬ç§ij
    0.07
    alloca
    0.07
    Activations Density 0.059%

    No Known Activations