© 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. 14535
    Prev
    Next
    INDEX
    Explanations

    ratio or Rate

    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
    çķ
    -0.06
    ç©·
    -0.06
    STS
    -0.06
    egu
    -0.06
    thon
    -0.06
    øg
    -0.06
    æī¿æĭħä¸ĢåĪĩ
    -0.06
    akes
    -0.06
    iami
    -0.06
     nexus
    -0.06
    POSITIVE LOGITS
    OrCreate
    0.09
    éħįæ¯Ķ
    0.08
    Ratio
    0.08
     ratio
    0.08
    æ´»åĮĸ
    0.08
    _ratio
    0.08
    edback
    0.08
    æ´»çļĦ
    0.08
    .active
    0.08
    两ç§įæĸ¹å¼ı
    0.08
    Activations Density 0.001%

    No Known Activations