© 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. 1397
    Prev
    Next
    INDEX
    Explanations

    levels of classification

    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
    以任ä½ķ
    -0.07
     harmon
    -0.07
     Slut
    -0.07
    设å®ļ
    -0.07
    檬
    -0.07
    竺
    -0.07
    æijĤ
    -0.07
    QUE
    -0.07
    forth
    -0.07
    çıĢ
    -0.07
    POSITIVE LOGITS
    åıĬ以ä¸ĭ
    0.08
     voire
    0.08
    ison
    0.07
    andle
    0.07
    oct
    0.07
    VICE
    0.07
    åıĬ以ä¸ĬçļĦ
    0.07
     promis
    0.07
    /gif
    0.07
    .promise
    0.07
    Activations Density 0.001%

    No Known Activations