© 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. 31839
    Prev
    Next
    INDEX
    Explanations

    percentage or quantity

    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
    recover
    -0.07
    enko
    -0.07
    లి
    -0.07
    chy
    -0.07
    _DL
    -0.06
    éĢĢåĽŀ
    -0.06
    å¤ļç§įæĸ¹å¼ı
    -0.06
     retract
    -0.06
    kle
    -0.06
    ê±°
    -0.06
    POSITIVE LOGITS
    ä¸ĭ游
    0.08
    ilent
    0.07
    ä»ĸæīĢ
    0.07
    atura
    0.07
    çĶ±åħ¶
    0.07
    ukkan
    0.07
    IDER
    0.07
    ider
    0.07
    extent
    0.07
     fullest
    0.07
    Activations Density 0.088%

    No Known Activations