© 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. 13687
    Prev
    Next
    INDEX
    Explanations

    crystal displays

    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
    GGLE
    -0.08
    çº
    -0.08
    hoot
    -0.07
    наÑĢ
    -0.07
    adre
    -0.07
    eties
    -0.07
    abee
    -0.07
    êµī
    -0.07
    bies
    -0.07
    dach
    -0.07
    POSITIVE LOGITS
    çĤ¹åĩ»æŁ¥çľĭ
    0.07
    elay
    0.07
     wrapped
    0.07
     application
    0.06
    ippers
    0.06
    åľ¨è¿Ļç§į
    0.06
     Mek
    0.06
    éĢ¸
    0.06
    wrapped
    0.06
    ip
    0.06
    Activations Density 0.460%

    No Known Activations