© 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. 56453
    Prev
    Next
    INDEX
    Explanations

    conic sections

    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
    èĢĥå®ĺ
    -0.08
    åѦåīį
    -0.07
    åħļ群
    -0.07
    æµ·é»ĺ
    -0.07
    ilton
    -0.07
    èľĪ
    -0.07
    á»Ļm
    -0.07
    ÙĬØŃ
    -0.07
    æĭ§
    -0.07
     Unicorn
    -0.07
    POSITIVE LOGITS
    æ¤Ń
    0.08
    æģĴå®ļ
    0.07
    æģĴ
    0.07
    तà¥įर
    0.07
    åħ¬åħĥåīį
    0.07
    ambul
    0.06
     arcs
    0.06
     pouch
    0.06
     distances
    0.06
     ellipt
    0.06
    Activations Density 0.001%

    No Known Activations