© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    actions and 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
    rames
    -0.10
    /from
    -0.10
    lash
    -0.09
    plevel
    -0.09
    -chief
    -0.09
    [email
    -0.09
    ående
    -0.09
    asilan
    -0.09
    scription
    -0.09
    -comments
    -0.08
    POSITIVE LOGITS
    /
    0.11
     up
    0.08
     out
    0.08
     upp
    0.07
    ald
    0.07
    ãĢģ
    0.07
    åĩº
    0.06
    /re
    0.06
    ä¹ĭ以
    0.06
    le
    0.06
    Activations Density 1.558%

    No Known Activations