© 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. 9726
    Prev
    Next
    INDEX
    Explanations

    TEXT following specific words

    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
    ¶
    -0.06
    obo
    -0.06
     Ven
    -0.06
    鼷
    -0.06
    ׳×ķ
    -0.06
     dec
    -0.06
     –**
    -0.06
     -**
    -0.06
    æĬĬä¸Ģ个
    -0.06
     Mour
    -0.06
    POSITIVE LOGITS
    undur
    0.08
     NOTICE
    0.07
    çļĦ空éĹ´
    0.07
    pun
    0.07
    ÑĢож
    0.07
    ymp
    0.07
     Sipil
    0.07
    è¿ľæµģ
    0.07
    ãĥ¡ãĥ¼ãĤ¸
    0.07
     excell
    0.07
    Activations Density 0.003%

    No Known Activations