© 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. 60845
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    AZE
    -0.10
    azed
    -0.10
    aze
    -0.09
    illons
    -0.09
    DITION
    -0.09
    iksa
    -0.09
    aza
    -0.09
    llib
    -0.09
    cola
    -0.09
    ANDA
    -0.09
    POSITIVE LOGITS
    0.10
    ļ
    0.08
    ĩ
    0.08
    /
    0.06
    -
    0.06
     bas
    0.06
    ±
    0.06
    ħ
    0.06
    Ĭ
    0.06
     le
    0.06
    Activations Density 0.004%

    No Known Activations