© 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. 61004
    Prev
    Next
    INDEX
    Explanations

    mechanism and operation explanations

    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
     aforementioned
    -0.10
    å¦Ĥä¸Ĭ
    -0.09
    ohon
    -0.09
    对ä¸Ĭè¿°
    -0.08
    éĢļè¿ĩ以ä¸Ĭ
    -0.08
    odox
    -0.08
    ην
    -0.07
    ä¸Ĭè¨ĺ
    -0.07
    åľ¨ä¸Ĭè¿°
    -0.07
    zog
    -0.07
    POSITIVE LOGITS
      ↵↵
    0.07
    âĢ¦*
    0.07
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    0.07
    æĪ¸
    0.07
    以åıĬ缸åħ³
    0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
    ÑĩÑij
    0.06
    ]').
    0.06
    ~-
    0.06
     useful
    0.06
    Activations Density 0.036%

    No Known Activations