© 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. 57770
    Prev
    Next
    INDEX
    Explanations

    yes or no confirmation

    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
    ).__
    -0.08
    alker
    -0.08
    erschaft
    -0.07
    '](
    -0.07
    abora
    -0.07
    _repr
    -0.07
    _CI
    -0.07
    çĥŃéŨæݨèįIJ
    -0.07
    _And
    -0.07
    ÑĦелÑĮ
    -0.07
    POSITIVE LOGITS
    ystone
    0.07
     Rag
    0.06
    hetto
    0.06
    enga
    0.06
     global
    0.06
     alternatively
    0.06
     Kir
    0.06
    orex
    0.06
    вÑĥ
    0.06
    akit
    0.06
    Activations Density 0.002%

    No Known Activations