© 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. 29501
    Prev
    Next
    INDEX
    Explanations

    face seal

    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
    ta
    -0.10
    ship
    -0.10
    ships
    -0.09
    ten
    -0.09
    ë¥ł
    -0.08
     ìĿ¸íķ´
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    fristig
    -0.08
    patrick
    -0.08
    ÑĤа
    -0.08
    POSITIVE LOGITS
     nạ
    0.12
    /or
    0.10
    hood
    0.10
    stry
    0.09
    ä¸ĬçļĦ
    0.09
     걸ì³IJ
    0.09
    åĽ¢çļĦ
    0.08
    ording
    0.08
     اÙĦÙĥرÙĬÙħ
    0.08
    eted
    0.08
    Activations Density 0.025%

    No Known Activations