© 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. 12464
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending sentences

    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
    incar
    -0.08
    ä¸įå¦Ĥ
    -0.08
    çļĦåı£
    -0.08
    nows
    -0.08
    -vs
    -0.07
    dont
    -0.07
    ezd
    -0.07
    zeug
    -0.07
    roda
    -0.07
    ovn
    -0.07
    POSITIVE LOGITS
    åį³åľ¨
    0.12
    çļĦéĤ£æł·
    0.11
    åį³
    0.11
    åį³ä»¥
    0.10
     yaitu
    0.10
     namely
    0.10
     ÛĮعÙĨÛĮ
    0.09
    `:
    0.09
     yakni
    0.09
    ":
    0.09
    Activations Density 0.187%

    No Known Activations