© 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. 55551
    Prev
    Next
    INDEX
    Explanations

    output or message display

    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
    iz
    -0.07
    iry
    -0.07
     bó
    -0.06
     bi
    -0.06
    æķ¦
    -0.06
    rel
    -0.06
    IZ
    -0.06
    è¿ĻäºĽä¸ľè¥¿
    -0.06
     opp
    -0.06
     relativ
    -0.06
    POSITIVE LOGITS
     waarbij
    0.09
    akon
    0.08
    vaard
    0.08
    azan
    0.08
     wherein
    0.08
    åħ±äº§
    0.08
    onnier
    0.08
    åı¯ä»¥çľĭåĩº
    0.07
    åīįåįĬ
    0.07
     waarin
    0.07
    Activations Density 0.110%

    No Known Activations