© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30032
    Prev
    Next
    INDEX
    Explanations

    conditions / architecture

    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
    lord
    -0.07
    ç¥ī
    -0.07
    iko
    -0.06
    ç¬
    -0.06
    ico
    -0.06
    è¾ŀ
    -0.06
    æĪĴ
    -0.06
    è¾Ł
    -0.06
    ä¸įæĪIJ
    -0.06
     opon
    -0.06
    POSITIVE LOGITS
    бой
    0.08
    ç¾İåĽ¾
    0.08
    untime
    0.07
    çant
    0.07
    again
    0.07
    .showMessage
    0.07
    è´ªåĽ¾
    0.07
    ImagePath
    0.07
    rensa
    0.07
    othi
    0.07
    Activations Density 0.025%

    No Known Activations