© 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. 7866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    dat
    -0.07
     Tent
    -0.07
    çĪĨ
    -0.07
    mk
    -0.06
    ндекÑģ
    -0.06
    /dat
    -0.06
    mpl
    -0.06
    .createObject
    -0.06
     dat
    -0.06
    DMA
    -0.06
    POSITIVE LOGITS
    etro
    0.07
    .scroll
    0.07
    bles
    0.07
    bind
    0.07
    owan
    0.07
    è´¢æĶ¿éĥ¨éŨ
    0.07
    agos
    0.07
    istel
    0.07
    çħ§å¸¸
    0.07
    æ¥
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.