© 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. 60361
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating completed actions

    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
    üst
    -0.08
    lick
    -0.08
    åįģäºĶç«ł
    -0.08
    该åĨħ容
    -0.08
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    -0.08
    æĬĬè¿Ļ个
    -0.08
    äºĨ解详æĥħ
    -0.08
    portiva
    -0.08
    æĬĬå®ĥ
    -0.08
    irma
    -0.08
    POSITIVE LOGITS
     by
    0.11
     تÙĪسط
    0.08
     bợi
    0.08
     oleh
    0.08
    by
    0.08
    afe
    0.08
    åģļ为
    0.07
    /upload
    0.07
    ä½ľä¸ºä¸Ģç§į
    0.07
    åĪĻçĶ±
    0.07
    Activations Density 0.803%

    No Known Activations