© 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. 63703
    Prev
    Next
    INDEX
    Explanations

    survival, copyright, or foreign words

    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
    åĽŀ头
    -0.08
    agger
    -0.07
    cape
    -0.07
    inkel
    -0.07
    é¦ĸéķ¿
    -0.07
    æĤī
    -0.06
    主èIJ¥
    -0.06
     équ
    -0.06
    ucker
    -0.06
    å¤į
    -0.06
    POSITIVE LOGITS
    ниÑĤ
    0.07
    almaz
    0.07
     Folg
    0.07
    etlen
    0.07
    åİ»ä½ķ
    0.07
    äºĶ常
    0.07
    OLER
    0.07
    pared
    0.07
    اص
    0.07
    åħĭåĪ©
    0.07
    Activations Density 0.001%

    No Known Activations