© 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. 30685
    Prev
    Next
    INDEX
    Explanations

    example or express state

    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
    åįİå±±
    -0.08
    Ñħодов
    -0.07
    ubin
    -0.06
    çݯèĬĤ
    -0.06
    Called
    -0.06
    icult
    -0.06
     Truth
    -0.06
    ubl
    -0.06
     imposing
    -0.06
    çļĦæľĢé«ĺ
    -0.06
    POSITIVE LOGITS
    表述
    0.10
    æĦıæĮĩ
    0.08
    পà§ģর
    0.08
    åĪ¤
    0.08
    oura
    0.07
    çIJĨ解为
    0.07
    éĤ¦
    0.07
    bdb
    0.07
     intended
    0.07
     intends
    0.07
    Activations Density 0.002%

    No Known Activations