© 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. 15652
    Prev
    Next
    INDEX
    Explanations

    impulse control

    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
    wards
    -0.09
    -0.09
    igans
    -0.08
    nement
    -0.08
    ä¹İä¹İçļĦ
    -0.07
    æĪijæĿ¥è¯´
    -0.07
    abouts
    -0.07
    ždy
    -0.07
    ¸
    -0.07
    oor
    -0.06
    POSITIVE LOGITS
    ive
    0.10
    ément
    0.09
    odie
    0.08
    à¸įา
    0.08
    ster
    0.08
    aneous
    0.08
    ognito
    0.08
    ยà¸Ńà¸Ķ
    0.08
    åį³éĢĿ
    0.08
    stick
    0.08
    Activations Density 0.043%

    No Known Activations