© 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. 28710
    Prev
    Next
    INDEX
    Explanations

    previously served

    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
    å¾Īå¿«çļĦ
    -0.07
    ingga
    -0.07
    å¾Īå¿«
    -0.07
    ä¸įæĢĿ
    -0.07
    ä¿ĬæĿ°
    -0.07
    indak
    -0.07
    å¼Ģå¼ł
    -0.06
    gens
    -0.06
    å¦ĤæľŁ
    -0.06
    åIJİè¦ģ
    -0.06
    POSITIVE LOGITS
     beforehand
    0.19
    åľ¨æѤä¹ĭåīį
    0.18
     preceding
    0.18
     préalable
    0.17
     terlebih
    0.15
     vorher
    0.15
    å¿ħé¡»åħĪ
    0.15
     zuvor
    0.15
    åħĪå¾Ĺ
    0.15
     préal
    0.15
    Activations Density 0.308%

    No Known Activations