© 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. 18065
    Prev
    Next
    INDEX
    Explanations

    series or serial connection

    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
    OrDefault
    -0.09
    essere
    -0.08
    grounds
    -0.08
    дай
    -0.08
    大èį¯æĪ¿
    -0.08
     betreff
    -0.08
    ambi
    -0.08
    tais
    -0.07
    ylum
    -0.07
    atsby
    -0.07
    POSITIVE LOGITS
    /on
    0.07
     nhau
    0.07
    åľ¨ä¸Ģèµ·çļĦ
    0.07
    -ish
    0.07
     traversal
    0.06
    aneous
    0.06
     looping
    0.06
     loop
    0.06
     sequentially
    0.06
    aneously
    0.06
    Activations Density 0.011%

    No Known Activations