© 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. 38375
    Prev
    Next
    INDEX
    Explanations

    domain names and contexts

    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
    缸è¾ħ缸æĪIJ
    -0.10
    tings
    -0.09
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
     volna
    -0.09
    ories
    -0.09
    аем
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    iget
    -0.08
    gnore
    -0.08
    dater
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.08
    -wide
    0.08
    åĪĨ许
    0.08
    UMMY
    0.07
    å¤ĸçļĦ
    0.07
    phin
    0.07
    Äįek
    0.07
    ictionaries
    0.07
    ughters
    0.07
    sWith
    0.07
    Activations Density 0.023%

    No Known Activations