© 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. 32177
    Prev
    Next
    INDEX
    Explanations

    remove suffix or extension

    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
    èĢĮä¸įæĺ¯
    -0.08
    èĢĮéĿŀ
    -0.08
    isci
    -0.08
    onde
    -0.07
     rather
    -0.07
     plutôt
    -0.06
     <<
    -0.06
    ä»ĸ们没æľī
    -0.06
     Beyond
    -0.06
    ä½łæ²¡æľī
    -0.06
    POSITIVE LOGITS
     altogether
    0.09
    éĢļè¿ĩå°Ĩ
    0.08
     indem
    0.08
    aras
    0.08
    害人
    0.08
    顾ä¹ĭ忧
    0.08
    æĸ¹ä¾¿äºĨ
    0.08
    letz
    0.07
    пÑĭ
    0.07
    åıªè¦ģåľ¨
    0.07
    Activations Density 0.021%

    No Known Activations