© 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. 9507
    Prev
    Next
    INDEX
    Explanations

    boundary tokens and control flow

    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
     Sullivan
    -0.09
     spherical
    -0.07
    stech
    -0.07
    olumbia
    -0.07
    ÑĩеÑĤов
    -0.07
    ilan
    -0.07
    dsm
    -0.07
    uldig
    -0.07
    aday
    -0.07
    ÙĪÙĦÙĬÙĨ
    -0.07
    POSITIVE LOGITS
    éĤ£å¤´
    0.08
    arak
    0.07
    ince
    0.07
     reducing
    0.07
    åĩıå°ij对
    0.07
    ingle
    0.06
    çĴĢ
    0.06
    ukaan
    0.06
    adero
    0.06
     reduction
    0.06
    Activations Density 0.001%

    No Known Activations