© 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. 65177
    Prev
    Next
    INDEX
    Explanations

    reactants followed by products

    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
    reicher
    -0.08
    alba
    -0.07
    ×¢×Ļ
    -0.07
    ãĤıãĤĬãģ«
    -0.07
    éĩ
    -0.07
    ĮĢ
    -0.07
    _DL
    -0.07
    ctest
    -0.07
    uce
    -0.07
    uga
    -0.07
    POSITIVE LOGITS
    åĩºåİ»çļĦ
    0.08
    влеÑĩениÑı
    0.07
    takt
    0.07
    tir
    0.07
    åĩºåİ»
    0.07
    ä¿
    0.07
    TING
    0.07
    czas
    0.07
    åĩºæĿ¥
    0.07
     liberated
    0.06
    Activations Density 0.004%

    No Known Activations