© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    spirits, gods, ghosts

    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
    ä¸įçł´
    -0.08
    被客æĪ·
    -0.08
    terminated
    -0.08
     пÑĢиго
    -0.08
    byss
    -0.08
    ারà§įথ
    -0.08
     zdoby
    -0.07
    tring
    -0.07
    vely
    -0.07
    echa
    -0.07
    POSITIVE LOGITS
     assistance
    0.07
    ä¿Ŀä½ij
    0.07
     invis
    0.07
    สà¸ĸ
    0.07
     invisible
    0.07
    åħ³çħ§
    0.07
    çľ·æģĭ
    0.07
    ijin
    0.06
    åĬ©
    0.06
    游
    0.06
    Activations Density 0.054%

    No Known Activations