© 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. 56079
    Prev
    Next
    INDEX
    Explanations

    past actions or prior 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
    resti
    -0.08
    ç´§æİ¥çĿĢ
    -0.08
    stel
    -0.08
    stk
    -0.07
    åĨįæİ¥
    -0.07
    ä¸ĭä¸Ģç«ł
    -0.07
     berlanjut
    -0.07
    ign
    -0.07
    çļĦæŶåĢĻ
    -0.07
    UTI
    -0.07
    POSITIVE LOGITS
     recientemente
    0.13
     recently
    0.11
     recentemente
    0.11
     been
    0.10
     already
    0.10
    并已
    0.10
     previously
    0.10
    been
    0.09
    ä¹Łå·²
    0.09
    Been
    0.09
    Activations Density 0.697%

    No Known Activations