© 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. 12483
    Prev
    Next
    INDEX
    Explanations

    programming terms followed by equals sign

    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
    ois
    -0.08
    ESH
    -0.08
    iam
    -0.07
    [url
    -0.07
    ajs
    -0.07
    pret
    -0.07
    ìĭ¬ìľ¼ë¡ľ
    -0.07
    iar
    -0.07
    ç«ĻåĪ°
    -0.07
    LOS
    -0.07
    POSITIVE LOGITS
    ุà¸Ķ
    0.07
    reopen
    0.07
    umbles
    0.07
    è¿Ļä¹Īä¸Ģ个
    0.07
    ¿
    0.06
    rag
    0.06
    boy
    0.06
    ä¿¡æģ¯åıijå¸ĥ
    0.06
    -proxy
    0.06
    ç¼ī
    0.06
    Activations Density 0.001%

    No Known Activations