© 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. 13559
    Prev
    Next
    INDEX
    Explanations

    first begins

    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
    ä¸įä»ħåľ¨
    -0.08
    ä¸įä»ħæľī
    -0.07
    .Wrap
    -0.07
    主è¦ģæĺ¯æĮĩ
    -0.07
    upro
    -0.07
    chia
    -0.07
    ä¸įè¿ľ
    -0.07
    åĮħæĭ¬äºĨ
    -0.06
    asto
    -0.06
    éĢĥèµ°
    -0.06
    POSITIVE LOGITS
    ä¸Ģå¼Ģå§ĭ
    0.12
    åĪĿå§ĭ
    0.12
     initially
    0.11
    èµ·åĪĿ
    0.11
     Initially
    0.11
    ä¸Ģéĸĭå§ĭ
    0.11
     first
    0.11
    第ä¸ĢæŃ¥
    0.11
    å¼Ģå§ĭæŶ
    0.10
     pertama
    0.10
    Activations Density 0.044%

    No Known Activations