© 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. 58675
    Prev
    Next
    INDEX
    Explanations

    variables:

    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
     []).
    -0.09
    égor
    -0.08
    oust
    -0.08
    urada
    -0.07
    /classes
    -0.07
    ][]
    -0.07
    osl
    -0.07
     "").
    -0.07
    биÑı
    -0.07
    алÑĮÑı
    -0.07
    POSITIVE LOGITS
    çī¹
    0.06
    ID
    0.06
    tha
    0.06
    verd
    0.06
    æİ
    0.06
    æĸĻ
    0.06
    IgnoreCase
    0.06
    âĢ¢
    0.06
    屿
    0.06
    çĶ¨äºİ
    0.06
    Activations Density 0.008%

    No Known Activations