© 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. 8722
    Prev
    Next
    INDEX
    Explanations

    imaginary direction

    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
    æľĪçĶŁ
    -0.07
    åħľ
    -0.07
    ant
    -0.07
    çĥģ
    -0.07
    _subtype
    -0.06
    å¦Ĥåħ¶
    -0.06
    lee
    -0.06
    人å¤ļ
    -0.06
    åħĭéļĨ
    -0.06
    à®°
    -0.06
    POSITIVE LOGITS
    å¸Ŀéĥ½
    0.09
    绣ä¸ĢæĢĿæĥ³
    0.08
    绣ä¸Ģ
    0.08
    绣ä¸ĢçļĦ
    0.08
    ä¸Ģä½ĵ
    0.07
     unified
    0.07
    éŃĶçİĭ
    0.07
    绣çŃ¹æİ¨è¿Ľ
    0.07
    ä¸Ģé«Ķ
    0.07
    ç»ĦæĪIJäºĨ
    0.07
    Activations Density 0.001%

    No Known Activations