© 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. 22049
    Prev
    Next
    INDEX
    Explanations

    foreign characters and symbols

    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
    ain
    -0.06
    à¸ĭา
    -0.06
    çµ
    -0.06
    éĢļè¿ĩ以ä¸Ĭ
    -0.06
     ë°°
    -0.06
    å°ĸåı«
    -0.06
    izia
    -0.06
    .conf
    -0.05
    بر
    -0.05
    gia
    -0.05
    POSITIVE LOGITS
    казÑĭ
    0.08
    ÃŃsmo
    0.08
     doule
    0.08
    dden
    0.08
    åıĪ称
    0.08
    ä¹ĭäºİ
    0.07
    (nd
    0.07
     literally
    0.07
    ueue
    0.07
    .den
    0.07
    Activations Density 0.446%

    No Known Activations