© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62731
    Prev
    Next
    INDEX
    Explanations

    past tense verb endings

    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
    istry
    -0.09
    ÙĪÙī
    -0.08
    imony
    -0.08
    ibility
    -0.08
    yme
    -0.08
    olist
    -0.08
    uits
    -0.08
    illy
    -0.08
    ick
    -0.08
    ouce
    -0.08
    POSITIVE LOGITS
    ated
    0.15
    ed
    0.14
    edList
    0.10
    áĥĶáĥijáĥ£áĥļáĥĺ
    0.10
    à¸ģัà¸Ļ
    0.10
    ATED
    0.10
    ected
    0.09
    çĿĢçļĦ
    0.09
    edBy
    0.09
    ados
    0.08
    Activations Density 0.169%

    No Known Activations