© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    redux saga, CT angiography, saddle bag, node group, pump register, TV Box, printer driver, graphene oxide

    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
    ichten
    -0.07
    å¿Ĺ强
    -0.06
    康
    -0.06
    usty
    -0.06
    orios
    -0.06
    ane
    -0.06
    eland
    -0.06
    á»ĭ
    -0.06
    ä¸Ģç¬ij
    -0.06
     Steele
    -0.06
    POSITIVE LOGITS
    ³
    0.08
    ecam
    0.07
    æ³¥
    0.07
    å¨ĺ
    0.06
    ogne
    0.06
    өл
    0.06
    fond
    0.06
     prohib
    0.06
    ukat
    0.06
     ['-
    0.06
    Activations Density 0.340%

    No Known Activations