© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    sequences starting sentences

    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
    "And
    -0.07
    irmed
    -0.07
    ãģĿãģ®ä»ĸãģ®
    -0.06
    otal
    -0.06
    uta
    -0.06
    .SDK
    -0.06
    ipe
    -0.06
     stderr
    -0.06
    dana
    -0.06
    etar
    -0.06
    POSITIVE LOGITS
     nemlig
    0.11
     Firstly
    0.11
    é¦ĸåħĪ
    0.10
    é¦ĸåħĪæĺ¯
    0.10
    éĤ£å°±æĺ¯
    0.10
     firstly
    0.09
     nämlich
    0.09
     namelijk
    0.09
     totiž
    0.09
     namely
    0.09
    Activations Density 0.727%

    No Known Activations