© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    bi, ni, or `i` followed by certain characters

    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
    lah
    -0.16
    à¸Ļà¹īà¸Ńย
    -0.16
    nya
    -0.15
    sWith
    -0.13
    la
    -0.12
    st
    -0.12
    ness
    -0.12
    ÙĨا
    -0.12
    à¸Ļาà¸Ļ
    -0.11
    à¸Ļีà¹Ī
    -0.11
    POSITIVE LOGITS
    ê¹IJ
    0.14
    Ò£
    0.12
    wujudkan
    0.11
    Ìģ
    0.11
    ãĤħãģĨ
    0.11
    wajibkan
    0.10
    èī²åĪĹ
    0.10
    ungkapkan
    0.10
    Úº
    0.10
    plier
    0.10
    Activations Density 1.452%

    No Known Activations