© 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. 29398
    Prev
    Next
    INDEX
    Explanations

    lymphoma and leukemia

    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
     Michelin
    -0.08
    éĺ²æ»ij
    -0.08
     Texans
    -0.07
    æºIJæ³ī
    -0.07
    ikli
    -0.07
    åij¨çļĦ
    -0.07
    轩è¾ķ
    -0.07
    æī¿åĮħåķĨ
    -0.06
    Planet
    -0.06
     Grie
    -0.06
    POSITIVE LOGITS
    æ·ĭå·´çĺ¤
    0.12
     leukemia
    0.10
    çĻ½è¡ĢçĹħ
    0.10
    çĻ½è¡Ģ
    0.09
    åĮĸçĸĹ
    0.08
    íĥģ
    0.08
    igel
    0.08
     Epstein
    0.08
    filtr
    0.08
     hemat
    0.08
    Activations Density 0.331%

    No Known Activations