© 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. 20195
    Prev
    Next
    INDEX
    Explanations

    perovskite, electric, titanate

    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
    è¡Įéģĵ
    -0.08
    Trees
    -0.08
    _trees
    -0.08
    æŀĹä¸ļå±Ģ
    -0.08
    åİŁæľ¨
    -0.08
     Tree
    -0.07
     trees
    -0.07
    æłijçļ®
    -0.07
     Trees
    -0.07
    æłijä¸Ĭ
    -0.07
    POSITIVE LOGITS
    çĵ·
    0.09
    æħµ
    0.09
    çłĮ
    0.09
    éĻ¶çĵ·
    0.09
    Tiles
    0.08
    æĬ¹
    0.08
    åªļ
    0.08
     ceramic
    0.08
     mili
    0.08
     Ceramic
    0.08
    Activations Density 0.033%

    No Known Activations