© 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. 63080
    Prev
    Next
    INDEX
    Explanations

    index 0 or zero

    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
    mk
    -0.08
    è¿Ļ个女人
    -0.08
    ämm
    -0.07
    midi
    -0.07
    ista
    -0.07
    estad
    -0.07
    ¼
    -0.07
    å¦ĥ
    -0.07
    cker
    -0.06
     "')
    -0.06
    POSITIVE LOGITS
    -best
    0.07
     ÙĪاÙĦØ«
    0.07
    ÏĦÏħ
    0.07
    osso
    0.07
    สุà¸Ķ
    0.07
    çĽ²äºº
    0.07
    ä¸į移
    0.07
    å¤ı令
    0.06
    漩
    0.06
    iale
    0.06
    Activations Density 0.013%

    No Known Activations