© 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. 57746
    Prev
    Next
    INDEX
    Explanations

    pancreatic cancer, peptides, submission

    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
    äl
    -0.07
    oi
    -0.07
    VERBOSE
    -0.06
    verband
    -0.06
    Jos
    -0.06
    çļĦ確
    -0.06
    vern
    -0.06
     alt
    -0.06
    ä»İéĤ£
    -0.06
    .cz
    -0.06
    POSITIVE LOGITS
    æľīçĤ¹åĥı
    0.10
    æ½ľåľ¨çļĦ
    0.10
     impending
    0.09
    åıijå±ķ为
    0.09
     resembles
    0.09
    åıijå±ķæĪIJ
    0.08
     вплоÑĤÑĮ
    0.08
    æĽ´æİ¥è¿ij
    0.08
     resembling
    0.08
     eventual
    0.08
    Activations Density 0.812%

    No Known Activations