© 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. 58001
    Prev
    Next
    INDEX
    Explanations

    Oreo, Ogg, Oly

    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
    -orange
    -0.11
     dioxide
    -0.09
    åĴĮä¹īåĬ¡
    -0.08
     обÑĢазом
    -0.08
    åĬŀåħ¬åİħ
    -0.07
    oning
    -0.07
    åħ®åħ®
    -0.07
    edly
    -0.07
    çī©åĬĽ
    -0.07
    åı£æľį液
    -0.06
    POSITIVE LOGITS
    verture
    0.16
    vertime
    0.15
    iginal
    0.14
    portun
    0.14
    yssey
    0.14
    'Connor
    0.14
    ÑĩеÑĢед
    0.14
    ÑĢанже
    0.13
    lymp
    0.13
    'Neill
    0.13
    Activations Density 0.959%

    No Known Activations