© 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. 50847
    Prev
    Next
    INDEX
    Explanations

    holy objects or people

    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
    å²Ľ
    -0.07
    黯
    -0.07
    æ¡£
    -0.06
     SL
    -0.06
    åIJĪãĤıãģĽ
    -0.06
    é²į
    -0.06
    天ç¥ŀ
    -0.06
    æĢ»ä½ĵ
    -0.06
    ä¸Ģåı¶
    -0.06
    Rod
    -0.06
    POSITIVE LOGITS
    remos
    0.09
    èIJ±
    0.08
    vel
    0.08
    iets
    0.08
    loom
    0.07
    尿管
    0.07
    schuld
    0.07
    hausen
    0.07
    plex
    0.07
    spir
    0.07
    Activations Density 0.047%

    No Known Activations