© 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. 41722
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    éĺľ
    -0.09
    pNet
    -0.09
    å¾Īå¿Ļ
    -0.08
    æĸĩ件æĪĸ
    -0.08
    rowse
    -0.08
    à¸ļำ
    -0.08
    impse
    -0.08
    æĸ¯åħĭ
    -0.08
    jähr
    -0.08
    请ä¸ĭè½½
    -0.08
    POSITIVE LOGITS
    0.07
    éĦĻ
    0.07
     humanos
    0.06
    fr
    0.06
    andos
    0.06
    æį¢
    0.06
    èĭĹ
    0.06
    Man
    0.06
    ãĥ¯
    0.05
    OF
    0.05
    Activations Density 0.148%

    No Known Activations