© 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. 12036
    Prev
    Next
    INDEX
    Explanations

    first problem

    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
    heu
    -0.08
    é»ĦæŁIJ
    -0.07
    odo
    -0.07
    zier
    -0.07
    uml
    -0.07
    ondre
    -0.07
    chia
    -0.07
    FIG
    -0.07
    Ø´Ùħ
    -0.07
    åIJĦè¡Į
    -0.07
    POSITIVE LOGITS
    åºı
    0.07
    op
    0.07
    空
    0.07
    apur
    0.06
    macros
    0.06
    ÑĩеÑĤа
    0.06
    .checked
    0.06
    çļĦåIJ§
    0.06
    pe
    0.06
    osi
    0.06
    Activations Density 0.227%

    No Known Activations