© 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. 19397
    Prev
    Next
    INDEX
    Explanations

    chemical elements, often in compounds or ions

    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
    ele
    -0.08
    ously
    -0.07
    er
    -0.07
    ↵
    -0.06
    nya
    -0.06
    -0.06
    mes
    -0.06
    ×Ļ×Ļ×Ŀ
    -0.06
    se
    -0.06
     ,
    -0.06
    POSITIVE LOGITS
    jenigen
    0.09
    âĤ«
    0.09
    zioni
    0.09
    -Fi
    0.09
    schluss
    0.09
    Allem
    0.09
    ahrung
    0.08
    scher
    0.08
    ìī½ê²Į
    0.08
    -President
    0.08
    Activations Density 0.047%

    No Known Activations