© 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. 31929
    Prev
    Next
    INDEX
    Explanations

    carbide or alloys

    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
    éĽı
    -0.07
    çĶŁæķĪ
    -0.07
     undone
    -0.06
    åıijçĶŁçļĦ
    -0.06
    ç®Ģåįķåľ°
    -0.06
    å¥Ĺè·¯
    -0.06
    æĬ½è±¡
    -0.06
    دÙħ
    -0.06
    绵
    -0.06
    ä»İ严
    -0.06
    POSITIVE LOGITS
    åħ·æľīèī¯å¥½çļĦ
    0.10
     alloy
    0.10
     alloys
    0.10
    ä¼ĺèī¯çļĦ
    0.09
    åIJĪéĩij
    0.09
    讲åłĤ
    0.09
     domestically
    0.09
    odox
    0.08
    åĪ¶æĪIJçļĦ
    0.08
    -backed
    0.08
    Activations Density 0.073%

    No Known Activations