© 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. 30021
    Prev
    Next
    INDEX
    Explanations

    scale, transform, rotate, zoom

    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
    anen
    -0.07
     longest
    -0.06
    æĬĦ
    -0.06
    åħī顾
    -0.06
    åĩĢ
    -0.06
    ields
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    antha
    -0.06
    ime
    -0.06
    è¡Ķ
    -0.06
    POSITIVE LOGITS
    缩æĶ¾
    0.10
     CGAffineTransform
    0.10
    à¸ļิà¸Ķ
    0.09
     scaleFactor
    0.09
    æīŃæĽ²
    0.09
    åĢįæķ°
    0.09
    è®Ĭå½¢
    0.08
     маÑģÑĪÑĤаб
    0.08
     distortion
    0.08
    .zoom
    0.08
    Activations Density 0.071%

    No Known Activations