© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13895
    Prev
    Next
    INDEX
    Explanations

    Ewing sarcoma, PEX, DILI, C-section

    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
    èµĭ
    -0.07
    åĪ«
    -0.07
    å¾ħ
    -0.07
    ymar
    -0.07
    gether
    -0.07
    æľĪæľĪ
    -0.07
    еÑĢбÑĥ
    -0.06
    quelle
    -0.06
    und
    -0.06
    ups
    -0.06
    POSITIVE LOGITS
    Cog
    0.09
    çīĪ车åŀĭ
    0.08
    åĽ¾çŃī
    0.08
    à¹Ģà¸Ĭีย
    0.08
    à¸Ķีย
    0.07
    ä¸Ĭè¿°ä½ľåĵģ
    0.07
     sì
    0.07
    ieli
    0.07
    ä¸ŃåĽ½åĪ¶éĢł
    0.07
    åİ¿æķĻèĤ²å±Ģ
    0.07
    Activations Density 0.878%

    No Known Activations