© 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. 58318
    Prev
    Next
    INDEX
    Explanations

    future and forward-looking 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
    ystone
    -0.08
    FromArray
    -0.07
    å½°
    -0.07
    QRST
    -0.06
    /string
    -0.06
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.06
    suma
    -0.06
    æĹĹé¼ĵ
    -0.06
    åħ¥å¾®
    -0.06
    ÑģоÑĢ
    -0.06
    POSITIVE LOGITS
     future
    0.21
    æľªæĿ¥
    0.21
    å¯¹æľªæĿ¥
    0.21
    future
    0.20
    æľªæĿ¥çļĦ
    0.20
    çļĦæľªæĿ¥
    0.20
     futuro
    0.19
    é¢Ħæµĭ
    0.19
    å±ķæľĽ
    0.19
    .future
    0.19
    Activations Density 0.325%

    No Known Activations