© 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. 43617
    Prev
    Next
    INDEX
    Explanations

    platinum and related precious metals

    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
    ÙĩÙĨ
    -0.07
    ÙĬص
    -0.07
    zz
    -0.07
    ucho
    -0.07
    aik
    -0.06
    enste
    -0.06
     взаимоÑģ
    -0.06
    sembl
    -0.06
    åĨ³
    -0.06
    åIJµ
    -0.06
    POSITIVE LOGITS
    adium
    0.09
    è´µéĩijå±ŀ
    0.08
    atinum
    0.08
    idium
    0.08
    å°Ĭè´µ
    0.08
     prezi
    0.08
    importe
    0.08
    奢åįİ
    0.08
    è´µéĩį
    0.08
     اÙĦÙħØ·ÙĦ
    0.08
    Activations Density 0.018%

    No Known Activations