© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    protease, proteases, proteinase, proteinases

    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
    æ°´çģ«
    -0.09
    .intersection
    -0.09
     tô
    -0.08
    Ïĥκε
    -0.08
    здо
    -0.07
    usercontent
    -0.07
    ç´łé¢ľ
    -0.07
    elsen
    -0.07
    çĤ¼ä¸¹
    -0.07
    intersection
    -0.07
    POSITIVE LOGITS
    èĽĭçĻ½éħ¶
    0.10
     enzymes
    0.09
    éħ¶
    0.09
    æĹłæĥħ
    0.09
    enz
    0.08
    æ´»æĢ§
    0.08
     enzym
    0.08
    æĭĨ
    0.08
     prote
    0.08
    ase
    0.08
    Activations Density 0.138%

    No Known Activations