© 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. 47109
    Prev
    Next
    INDEX
    Explanations

    Assistant sub-inspector

    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
    cking
    -0.08
    rap
    -0.07
    itz
    -0.07
    èĮ¨
    -0.06
    èIJį
    -0.06
    ese
    -0.06
    åĪ«è¯´
    -0.06
     ש׾×IJ
    -0.06
    éĢģåİ»
    -0.06
    epage
    -0.06
    POSITIVE LOGITS
     favourable
    0.08
    arrera
    0.07
    Ïģιο
    0.07
    Õ»
    0.07
    asilan
    0.07
    dog
    0.07
     jednos
    0.07
    iven
    0.07
    æld
    0.07
    å¿ĻçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations