© 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. 1152
    Prev
    Next
    INDEX
    Explanations

    supporting, adjunct, secondary roles

    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
    ennem
    -0.08
    emar
    -0.07
    è°£
    -0.07
    çĥĻåį°
    -0.07
    Õ¡Õ°
    -0.07
    ابÛĮ
    -0.07
    icont
    -0.07
     bezo
    -0.07
    è¿Ī
    -0.07
    اص
    -0.07
    POSITIVE LOGITS
    次è¦ģ
    0.14
    éħįè§Ĵ
    0.14
    è¾ħåĬ©
    0.13
     subsidiary
    0.12
    Secondary
    0.11
     secondary
    0.11
    éĻĦå±ŀ
    0.11
     вÑģпом
    0.11
    secondary
    0.11
    è¼ĶåĬ©
    0.11
    Activations Density 0.203%

    No Known Activations