© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    potential

    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
     maxlen
    -0.08
    olim
    -0.07
    emen
    -0.07
    emor
    -0.07
    yaw
    -0.07
    zeug
    -0.07
    ivel
    -0.07
     count
    -0.07
    ç»ĵè´¦
    -0.07
    çĴĢ
    -0.06
    POSITIVE LOGITS
    ois
    0.08
    éĿĻçĶµ
    0.08
    éļľ
    0.08
    ä¸Ģ路走æĿ¥
    0.07
     piè
    0.07
    èµ·ä¼ı
    0.07
    è
    0.07
    ä¸ĢæĪIJ
    0.07
    ucr
    0.07
    jal
    0.07
    Activations Density 0.002%

    No Known Activations