© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    temporary or incidental citations

    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
    eiros
    -0.07
    Looper
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    razier
    -0.07
    anson
    -0.07
     Setter
    -0.07
    .setHeader
    -0.06
    »:
    -0.06
     mechanic
    -0.06
    åįģä½³
    -0.06
    POSITIVE LOGITS
     fleeting
    0.08
     incidental
    0.07
    yu
    0.07
     кÑĢаÑĤ
    0.07
    unfinished
    0.07
    dummy
    0.07
    yor
    0.07
    çŁŃæļĤ
    0.07
    ä»ij
    0.07
    temporary
    0.07
    Activations Density 1.174%

    No Known Activations