© 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. 10320
    Prev
    Next
    INDEX
    Explanations

    bullet points and symbols

    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
    åĪĨå¤ĸ
    -0.07
    对åIJ§
    -0.07
    ä¸IJ
    -0.06
    çĶ±æѤ
    -0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.06
    .wrapper
    -0.06
    رÙĥ
    -0.06
    تÙĩÙħ
    -0.06
    اÙĨÛĮ
    -0.06
    afen
    -0.06
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.08
    énk
    0.07
    лÑĮкÑĥ
    0.07
    czyk
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    EAU
    0.07
    ligh
    0.07
    abez
    0.07
    ächst
    0.07
    Activations Density 0.002%

    No Known Activations