© 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. 55828
    Prev
    Next
    INDEX
    Explanations

    precursor

    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
     Alison
    -0.07
     alignment
    -0.07
    TRE
    -0.06
     Gran
    -0.06
    éļĪ
    -0.06
     aligned
    -0.06
    wai
    -0.06
     reinforcing
    -0.06
    anda
    -0.06
     concurrent
    -0.06
    POSITIVE LOGITS
     indirectly
    0.16
    éĹ´æİ¥
    0.16
     indire
    0.14
     indirect
    0.13
    转åĮĸæĪIJ
    0.12
    转åĮĸ为
    0.11
    转æį¢æĪIJ
    0.10
     INDIRECT
    0.10
    æĬĺç®Ĺ
    0.10
    为åİŁæĸĻ
    0.09
    Activations Density 0.396%

    No Known Activations