© 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. 39146
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    å¾Īå¿Ļ
    -0.08
    éķ
    -0.08
    æĭīå°Ķ
    -0.07
     fundra
    -0.07
    еÑģÑĤво
    -0.07
    еÑģÑĤв
    -0.07
    ANNER
    -0.07
    ruf
    -0.07
    ä¸įè°ĥ
    -0.07
    ahi
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    wan
    0.07
    ri
    0.06
    TypeInfo
    0.06
    hs
    0.06
     Magn
    0.06
    andal
    0.06
    çľĭåľ¨çľ¼éĩĮ
    0.06
    bel
    0.06
    ji
    0.06
    Activations Density 0.785%

    No Known Activations