© 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. 25992
    Prev
    Next
    INDEX
    Explanations

    assembling materials or process steps

    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
    esis
    -0.07
    åħ¶ä»ĸçļĦ
    -0.07
    _rename
    -0.07
    vena
    -0.06
    ska
    -0.06
    arness
    -0.06
    çݯèĬĤ
    -0.06
    СÐIJ
    -0.06
    -fw
    -0.06
    ÑĩеÑĤ
    -0.06
    POSITIVE LOGITS
     newly
    0.09
     resulting
    0.09
     полÑĥÑĩен
    0.09
     newfound
    0.09
     gewonnen
    0.08
     полÑĥÑĩеннÑĭе
    0.08
     полÑĥÑĩеннÑĭÑħ
    0.08
     entstand
    0.08
     assembled
    0.07
    æĸ°çĶŁçļĦ
    0.07
    Activations Density 0.078%

    No Known Activations