© 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. 8741
    Prev
    Next
    INDEX
    Explanations

    postpones, curing, causes, leading, providing, ensuring

    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
    à¸į
    -0.09
    Due
    -0.08
     due
    -0.08
     _______,
    -0.08
    due
    -0.07
     because
    -0.07
    å°Ķå¾·
    -0.07
    éĥ½æĺ¯çĶ±
    -0.07
     tellement
    -0.07
    çĶ±äºİåħ¶
    -0.07
    POSITIVE LOGITS
    åıįèĢĮä¼ļ
    0.08
    éĻ¤éĿŀ
    0.08
    croll
    0.08
    åıįèĢĮæĺ¯
    0.08
     salvo
    0.07
    gelt
    0.07
    æķ¢è¯´
    0.07
     вплоÑĤÑĮ
    0.07
    æģŃåĸľ
    0.07
    otope
    0.07
    Activations Density 0.044%

    No Known Activations