© 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. 19062
    Prev
    Next
    INDEX
    Explanations

    then followed by completion

    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
    说åĪ°
    -0.06
     spoiled
    -0.06
    edal
    -0.06
     consistently
    -0.06
    çĪ±ä¸į
    -0.06
     catching
    -0.06
    说起
    -0.06
     interf
    -0.06
    ear
    -0.06
    èģĶ系客æľį
    -0.05
    POSITIVE LOGITS
     finally
    0.12
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    0.12
     enfin
    0.12
     further
    0.11
     наконеÑĨ
    0.11
    ä»Ĭ度ãģ¯
    0.11
    è¿Ľä¸ĢæŃ¥æī©å¤§
    0.11
    åĨį次
    0.11
    è¿Ľä¸ĢæŃ¥
    0.11
    è¿Ľä¸ĢæŃ¥æ·±åĮĸ
    0.11
    Activations Density 0.206%

    No Known Activations