© 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. 24658
    Prev
    Next
    INDEX
    Explanations

    outdoor structures and amenities

    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
     inside
    -0.06
    åľ°éĵģ
    -0.06
    森æŀĹéĩĮ
    -0.06
     subway
    -0.06
    çŀ¬æģ¯
    -0.06
     intense
    -0.06
    迷宫
    -0.06
     special
    -0.06
     layered
    -0.06
    è½®èĪ¹
    -0.06
    POSITIVE LOGITS
     backyard
    0.11
     homeowner
    0.09
     driveway
    0.09
    deaux
    0.09
    建æĪIJåIJİ
    0.08
     homeowners
    0.08
     landscaping
    0.08
    yard
    0.08
    æľ¬æĬ¥
    0.08
    éĢĨåıĺ
    0.08
    Activations Density 0.107%

    No Known Activations