© 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. 25301
    Prev
    Next
    INDEX
    Explanations

    dehydrogenase

    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
    å¦Ĥçİī
    -0.07
     kik
    -0.06
    áĢľáĢŃáĢ¯
    -0.06
    ivi
    -0.06
    åĺī
    -0.06
     اÙĦØŃص
    -0.06
    aneo
    -0.06
     softer
    -0.06
     défaut
    -0.06
    /response
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    åħīå±±
    0.07
    uards
    0.07
    ANNOT
    0.07
     Bethesda
    0.07
    æķ¬è¯·åħ³æ³¨
    0.07
    è¨Ŀ
    0.07
    以太
    0.07
    anded
    0.07
    opa
    0.07
    Activations Density 0.013%

    No Known Activations