© 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. 64763
    Prev
    Next
    INDEX
    Explanations

    cancer cell line

    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
    ug
    -0.07
    ç¬
    -0.07
    çĭ¬ç«ĭæĢĿèĢĥ
    -0.07
    odle
    -0.06
    ãĤ¦ãĥī
    -0.06
    çIJ¶
    -0.06
     boc
    -0.06
    RAR
    -0.06
    ekom
    -0.06
    对个人
    -0.06
    POSITIVE LOGITS
    åŀĭåı·çļĦ
    0.08
    ween
    0.08
    大çĻ½
    0.08
    ä¿ĬæĿ°
    0.08
    å¤§åľ£
    0.07
    à¸Ľà¸£
    0.07
    ترÛĮ
    0.07
    å°Ĭ
    0.07
    zit
    0.07
    å¿ĹåĪļ
    0.07
    Activations Density 0.202%

    No Known Activations