© 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. 56488
    Prev
    Next
    INDEX
    Explanations

    B followed by numbers or IO

    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
    .extract
    -0.07
    éĢĥçĶŁ
    -0.07
    æķij人
    -0.06
    è¯ķéªĮåĮº
    -0.06
    éŃĤ
    -0.06
    гоÑĢа
    -0.06
    æ¯Ľ
    -0.06
    å¸Ĥåľºä¸ĬçļĦ
    -0.06
     continent
    -0.06
     extraction
    -0.06
    POSITIVE LOGITS
    èıĮ
    0.11
    ç»ĨèıĮ
    0.09
     microbi
    0.09
    å¾®çĶŁçī©
    0.09
     bacteria
    0.09
     bacterial
    0.09
     bacter
    0.09
     бакÑĤеÑĢ
    0.08
    èıĮ群
    0.08
    éħµæ¯į
    0.08
    Activations Density 0.093%

    No Known Activations