© 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. 15292
    Prev
    Next
    INDEX
    Explanations

    consulting pomexplorer

    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
    ht
    -0.07
    гам
    -0.06
    DS
    -0.06
     interest
    -0.06
    临
    -0.06
     Wis
    -0.06
    ger
    -0.06
    лав
    -0.06
    hd
    -0.06
    åħ´è¶£
    -0.06
    POSITIVE LOGITS
    etine
    0.08
    äl
    0.08
    ilog
    0.08
    ukk
    0.08
    大亨
    0.08
    aix
    0.08
    iette
    0.07
    ÏģÏĨ
    0.07
    waran
    0.07
    Shown
    0.07
    Activations Density 0.456%

    No Known Activations