© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 45759
    Prev
    Next
    INDEX
    Explanations

    cardiovascular disease and headaches

    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
    pha
    -0.07
     Gaines
    -0.07
    ÑĪе
    -0.07
    æŀľ
    -0.07
     Rams
    -0.07
    åĢ©
    -0.07
    stag
    -0.06
    ÙĤÙĦÙĬ
    -0.06
     [+]
    -0.06
    åĦĢ
    -0.06
    POSITIVE LOGITS
    —including
    0.10
    åı¯èĥ½å°±æĺ¯
    0.10
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
    çļĦå°±æĺ¯
    0.09
    åĮħæĭ¬
    0.08
    ä¸įå°±æĺ¯
    0.08
     including
    0.08
    主è¦ģå°±æĺ¯
    0.08
    èĢĮè¿ĻäºĽ
    0.08
    represented
    0.07
    Activations Density 0.065%

    No Known Activations