© 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. 8984
    Prev
    Next
    INDEX
    Explanations

    world-wide-web

    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
     Colombo
    -0.07
    工人
    -0.06
    ä¸Ģ家
    -0.06
    hing
    -0.06
    ä¸Ĭä¸ĭçıŃ
    -0.06
    综åIJĪæĢ§
    -0.06
    çĶ»
    -0.06
    æ¿Ĵ
    -0.06
    .family
    -0.06
     Poe
    -0.06
    POSITIVE LOGITS
     recipro
    0.09
     reciprocal
    0.08
    /native
    0.08
    Inverse
    0.08
    èģĨ
    0.08
     взаим
    0.08
    inverse
    0.08
    æĺİå¾·
    0.07
     nghá»ĭch
    0.07
    éĢĨ
    0.07
    Activations Density 0.004%

    No Known Activations