© 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. 4431
    Prev
    Next
    INDEX
    Explanations

    sensor

    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
     اÙĦÙħتØŃدة
    -0.08
    çīĩæľº
    -0.07
    odob
    -0.07
    erton
    -0.07
    sver
    -0.07
    away
    -0.07
    ặng
    -0.07
    itioner
    -0.06
    çĶļèĢħ
    -0.06
     ÑĤаки
    -0.06
    POSITIVE LOGITS
     orario
    0.09
    acruz
    0.09
    thern
    0.09
    лÑĮкÑĥ
    0.08
    лага
    0.08
    imbra
    0.08
    à¹ĩ
    0.08
    jual
    0.08
    grade
    0.08
    aglio
    0.08
    Activations Density 0.034%

    No Known Activations