© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20371
    Prev
    Next
    INDEX
    Explanations

    phylogenetic

    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
    æĪĸå°ij
    -0.07
    ãi
    -0.06
    urier
    -0.06
    ãģ¤ãģ¶
    -0.06
    æ·¤
    -0.06
    å·¥ä¸ļåįıä¼ļ
    -0.06
    人以ä¸ĭ
    -0.06
    plier
    -0.06
     nostalg
    -0.06
     kohta
    -0.06
    POSITIVE LOGITS
    etic
    0.09
    umbu
    0.09
     tree
    0.08
    chon
    0.08
    ä¸ī代
    0.08
    /tree
    0.08
    æłijä¸Ĭ
    0.08
    ferences
    0.08
    etically
    0.08
     trùng
    0.08
    Activations Density 0.033%

    No Known Activations