© 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. 39582
    Prev
    Next
    INDEX
    Explanations

    replacement from, movement analysis, Race Died, fliximab, Mar Top

    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
    oload
    -0.08
    VERR
    -0.08
    ÙĨاد
    -0.08
    oppins
    -0.08
    egot
    -0.08
    èĤª
    -0.08
    ernals
    -0.07
    lopedia
    -0.07
    åķĨæĬ¥
    -0.07
    iranya
    -0.07
    POSITIVE LOGITS
    úa
    0.07
    ä¸įåİĮ
    0.07
    adu
    0.06
    stig
    0.06
    æīĢæĢĿ
    0.06
    ako
    0.06
    è¬Ļ
    0.06
    иÑģÑĥ
    0.06
    WND
    0.06
    PUR
    0.06
    Activations Density 0.868%

    No Known Activations