© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17582
    Prev
    Next
    INDEX
    Explanations

    text starting with contractions or words like explore

    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
    åºĶ该æľī
    -0.08
    âĢIJ
    -0.08
     Whereas
    -0.08
     everybody
    -0.08
     basically
    -0.08
     whilst
    -0.07
    å·²ç»ı被
    -0.07
    å¿ħé¡»è¦ģ
    -0.07
    ä¸Ģåħ±æľī
    -0.07
     purposely
    -0.07
    POSITIVE LOGITS
      ↵
    0.10
    —or
    0.10
    —but
    0.10
      ↵↵
    0.09
    )—
    0.09
    —and
    0.09
     foundational
    0.09
     [@
    0.08
     ($_
    0.08
    âĤĢ
    0.08
    Activations Density 0.581%

    No Known Activations