© 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. 24268
    Prev
    Next
    INDEX
    Explanations

    coral reefs and diving

    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
    -0.07
     Vector
    -0.06
    1
    -0.06
    ä¹Įäºij
    -0.06
    å¤§åľ°
    -0.06
    éĩİåħ½
    -0.06
    符
    -0.06
     execution
    -0.06
     vector
    -0.06
    çķ
    -0.06
    POSITIVE LOGITS
     reefs
    0.11
    ç¤ģ
    0.10
     Reef
    0.10
     reef
    0.09
    碳éħ¸éĴĻ
    0.09
     arrec
    0.09
    壽
    0.09
     underwater
    0.09
    ssc
    0.09
     Prost
    0.09
    Activations Density 0.039%

    No Known Activations