© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    transformations and changes

    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
    abe
    -0.08
     Trab
    -0.08
    üren
    -0.08
    ÙĬض
    -0.07
    ignant
    -0.07
    знание
    -0.07
    zeni
    -0.07
    ÑĢока
    -0.07
    æīįèĥ½æľī
    -0.07
    åĪ°åºķæľīå¤ļ
    -0.07
    POSITIVE LOGITS
     alteration
    0.14
     transformations
    0.14
    æĶ¹åıĺ
    0.14
    æĶ¹åĬ¨
    0.13
    çļĦæĶ¹åıĺ
    0.13
     transformation
    0.13
     alterations
    0.13
     changes
    0.13
    æĶ¹éĢł
    0.13
    æĽ´æĶ¹
    0.12
    Activations Density 0.685%

    No Known Activations