© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25122
    Prev
    Next
    INDEX
    Explanations

    faster, efficiency, best

    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
    Eventually
    -0.07
    è´§
    -0.06
     datum
    -0.06
    çĴĭ
    -0.06
    çļĦæł¸å¿ĥ
    -0.06
    åĬł
    -0.06
    ÑĮ
    -0.06
    ace
    -0.06
    çĶļèĩ³
    -0.06
    1
    -0.06
    POSITIVE LOGITS
    oge
    0.08
    plx
    0.07
    à¸Ĺาà¸ĩà¸ģาร
    0.07
    zni
    0.07
    BLUE
    0.07
    ceph
    0.07
    리ìĸ´
    0.07
    Mine
    0.07
    vere
    0.07
    oard
    0.07
    Activations Density 0.002%

    No Known Activations