© 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. 39089
    Prev
    Next
    INDEX
    Explanations

    /bin/env and commands

    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
    quo
    -0.07
    anes
    -0.07
    achers
    -0.07
    vég
    -0.06
    -0.06
     Ñģобой
    -0.06
    大æĪIJ
    -0.06
    ä¸Ģæī¶
    -0.06
    arts
    -0.06
    aders
    -0.06
    POSITIVE LOGITS
     accordingly
    0.08
    å¦Ĥä¸ĭ
    0.08
    ing
    0.07
    ãĥĩãĤ£ãĤª
    0.07
    eos
    0.07
    åħ¶ä¸º
    0.07
     từng
    0.06
    ING
    0.06
     via
    0.06
    ï¼ļ
    0.06
    Activations Density 0.014%

    No Known Activations