© 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. 8988
    Prev
    Next
    INDEX
    Explanations

    temporal references or past events

    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
    ordin
    -0.07
    lop
    -0.07
    lops
    -0.07
    dee
    -0.06
     pura
    -0.06
    å¢ĥåĨħçļĦ
    -0.06
    .sourceforge
    -0.06
    uzu
    -0.06
    ldata
    -0.06
     propri
    -0.06
    POSITIVE LOGITS
     earlier
    0.12
    æĪij们已ç»ı
    0.10
     Earlier
    0.09
    说è¿ĩ
    0.09
    Earlier
    0.09
     вÑĭÑĪе
    0.09
     سابÙĤ
    0.08
     already
    0.08
     above
    0.08
     سابÙĤØ©
    0.08
    Activations Density 0.351%

    No Known Activations