© 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. 41447
    Prev
    Next
    INDEX
    Explanations

    John, Susan, pizza

    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
    ç¬ijåĤ²
    -0.07
    åĿĤ
    -0.07
    aha
    -0.07
    este
    -0.07
    erot
    -0.07
    veget
    -0.07
    çĺ¾
    -0.06
    .escape
    -0.06
    agro
    -0.06
    çĽ¸ä¿¡åľ¨
    -0.06
    POSITIVE LOGITS
     arran
    0.07
    odon
    0.07
    /stretch
    0.07
    áĪµ
    0.07
    ajaran
    0.07
    aian
    0.07
    é¾Ļçľ¼
    0.07
    icule
    0.07
    áĢ²
    0.06
    пÑĤ
    0.06
    Activations Density 0.006%

    No Known Activations