© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39605
    Prev
    Next
    INDEX
    Explanations

    interaction, exchange, electron, dynamics

    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
    èĶĵ延
    -0.07
    è¸ıæŃ¥
    -0.07
    èĦļè¸ı
    -0.07
    itu
    -0.06
    .pull
    -0.06
    иÑĢаÑĤÑĮ
    -0.06
     humming
    -0.06
    mel
    -0.06
    æ»ħ
    -0.06
     drowning
    -0.06
    POSITIVE LOGITS
     interaction
    0.09
    interaction
    0.09
    è¿ijè·Ŀ离
    0.08
     تبادÙĦ
    0.08
    /contact
    0.08
     exchange
    0.08
    æį¢æĸ°
    0.08
     exchanged
    0.08
    Interaction
    0.08
    交æį¢
    0.08
    Activations Density 0.002%

    No Known Activations