© 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. 30166
    Prev
    Next
    INDEX
    Explanations

    connection apparatus or interface

    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
     pur
    -0.07
    ikai
    -0.06
    -0.06
     ãĢģ
    -0.06
    ard
    -0.06
     st
    -0.06
    åIJĦæĹı人æ°ij
    -0.06
    äºī
    -0.06
     Ko
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
    ansir
    0.09
    racle
    0.08
    fek
    0.07
     جرا
    0.07
    rique
    0.07
    èĨļ
    0.07
    alde
    0.07
    svar
    0.07
     **:**
    0.07
    reis
    0.07
    Activations Density 0.309%

    No Known Activations