© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17583
    Prev
    Next
    INDEX
    Explanations

    terminal, supply, channel, wall, backlight

    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
    é½IJåħ¨
    -0.08
    маÑı
    -0.08
    ÑĢÑĥд
    -0.07
     Nia
    -0.07
    éĽĨä¸ŃçļĦ
    -0.07
    anci
    -0.07
    æľīåij³
    -0.06
    reat
    -0.06
     Aga
    -0.06
     bern
    -0.06
    POSITIVE LOGITS
    enh
    0.08
    sec
    0.07
    大æīĭ
    0.07
     Leist
    0.07
    éĿŀ常éĢĤåIJĪ
    0.07
    åħµåĻ¨
    0.06
    лека
    0.06
    OSC
    0.06
    _svc
    0.06
    hak
    0.06
    Activations Density 0.212%

    No Known Activations