© 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. 14439
    Prev
    Next
    INDEX
    Explanations

    medical supplies

    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
    æŁIJäºĽ
    -0.09
     certain
    -0.08
    æķħæĦı
    -0.07
    åľ¨æŁIJäºĽ
    -0.07
     sometimes
    -0.07
    Certain
    -0.06
    çĽ¸å¯¹æ¯Ķè¾ĥ
    -0.06
     intentionally
    -0.06
    å°±æĭ¿
    -0.06
    æķħæĦıçļĦ
    -0.06
    POSITIVE LOGITS
     preferably
    0.12
    èĩ³å°ij
    0.11
     almeno
    0.10
    尤为éĩįè¦ģ
    0.09
    ä¸įå°ijäºİ
    0.09
     setidaknya
    0.09
     mindestens
    0.09
    èĩ³å°ijæľī
    0.09
    èĩ³å°ijåľ¨
    0.09
    prefer
    0.09
    Activations Density 0.017%

    No Known Activations