© 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. 28357
    Prev
    Next
    INDEX
    Explanations

    citation authorship and metadata

    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
    éĤ£ä¹Īåľ¨
    -0.07
     either
    -0.07
    ful
    -0.07
    裾
    -0.07
     EITHER
    -0.06
    onald
    -0.06
    arr
    -0.06
    |-
    -0.06
    dae
    -0.06
     Vict
    -0.06
    POSITIVE LOGITS
    -editor
    0.08
    markup
    0.07
    ä¸ļ
    0.07
    posito
    0.07
    usen
    0.07
    zen
    0.07
    åĬłç´¢
    0.07
    á»ijt
    0.06
    ä»Ģ
    0.06
    getBlock
    0.06
    Activations Density 0.004%

    No Known Activations