© 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. 29542
    Prev
    Next
    INDEX
    Explanations

    order of operations

    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
    ilde
    -0.08
    idez
    -0.08
    ะ
    -0.07
    <|fim_suffix|>
    -0.07
    æĥ³åIJĥ
    -0.07
    波波
    -0.07
     upps
    -0.06
    .Fragment
    -0.06
     Forte
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
    dü
    0.07
    奥å°Ķ
    0.07
    .Dev
    0.07
    Õµ
    0.07
    dev
    0.07
    vani
    0.06
     Erst
    0.06
    Æ¡n
    0.06
    ä»İä¸ļ
    0.06
    olis
    0.06
    Activations Density 0.003%

    No Known Activations