© 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. 25474
    Prev
    Next
    INDEX
    Explanations

    System; using

    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
    idin
    -0.07
    িপ
    -0.07
    åĪ¹éĤ£éĹ´
    -0.07
    iono
    -0.06
     digit
    -0.06
     espan
    -0.06
    纹
    -0.06
    digit
    -0.06
    ä»Ģä¹Īéĥ½æ²¡æľī
    -0.06
    idian
    -0.06
    POSITIVE LOGITS
    nets
    0.08
    ewood
    0.08
    -pad
    0.08
    äºĮä½į
    0.07
    emas
    0.07
    usia
    0.07
    amma
    0.07
    ä»ħä»£è¡¨ä½ľèĢħ
    0.07
    ķ
    0.07
    ä¸ĥ大
    0.07
    Activations Density 0.002%

    No Known Activations