© 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. 64593
    Prev
    Next
    INDEX
    Explanations

    Panel Set, Ruler Blog, encoded =

    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
    itude
    -0.07
     Gardner
    -0.07
    åĪ«èĩ´
    -0.07
    äºİè¡Į
    -0.06
    å¾ģéĢĶ
    -0.06
    åĬłæĭ¿å¤§çļĦ
    -0.06
    oward
    -0.06
    زاÙĦ
    -0.06
    墨å°Ķ
    -0.06
    æĩ¿
    -0.06
    POSITIVE LOGITS
    .nodes
    0.07
    å¹³éĺ³
    0.06
    barang
    0.06
    à¹Īว
    0.06
    å©Ĩ
    0.06
    å°§
    0.06
     bâ
    0.06
    Õ¸Õ²
    0.06
    ensive
    0.06
     Dee
    0.06
    Activations Density 0.062%

    No Known Activations