© 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. 58426
    Prev
    Next
    INDEX
    Explanations

    few days, weeks, seconds, minutes, files, essays

    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
    urga
    -0.08
     Ganze
    -0.08
    arians
    -0.08
    umpf
    -0.07
    Ïĥία
    -0.07
    zony
    -0.07
     Andi
    -0.07
    ï¾ŀ
    -0.07
    æv
    -0.07
    æĤłä¹ħçļĦ
    -0.07
    POSITIVE LOGITS
    ness
    0.12
     dozen
    0.11
     hundred
    0.09
     wenige
    0.09
    ëªĩ
    0.08
    ings
    0.08
    NESS
    0.08
    teenth
    0.07
    est
    0.07
    ishing
    0.07
    Activations Density 0.043%

    No Known Activations