© 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. 20917
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and proximity

    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
    ä¸įæĢĿ
    -0.09
    husus
    -0.08
    åı«å¥¹
    -0.07
    Posting
    -0.07
    ç¥ŀå±±
    -0.07
    ammers
    -0.07
    íĹĪ
    -0.07
    yarat
    -0.07
     Californ
    -0.07
    åĬłå°Ķ
    -0.07
    POSITIVE LOGITS
     smoothly
    0.08
    Near
    0.07
    near
    0.07
     nearby
    0.07
    lice
    0.07
    близи
    0.07
    å¹³æ»ij
    0.07
    лом
    0.07
     gần
    0.06
     proximity
    0.06
    Activations Density 0.004%

    No Known Activations