© 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. 16303
    Prev
    Next
    INDEX
    Explanations

    file paths and code imports

    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
     ((*
    -0.07
    ØŃر
    -0.06
    tof
    -0.06
    çªĸ
    -0.06
    æĢ»æ¯Ķ
    -0.06
    iy
    -0.06
    tn
    -0.06
    z
    -0.06
    æĥij
    -0.06
    寮
    -0.06
    POSITIVE LOGITS
    éłĵ
    0.08
    iches
    0.08
    /umd
    0.08
    .instrument
    0.07
    yped
    0.07
    eldon
    0.07
     Constructs
    0.07
    å®ļä¹īçļĦ
    0.07
    ä»Ĭå¹´æĺ¯
    0.07
    _lite
    0.07
    Activations Density 0.163%

    No Known Activations