© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    total of

    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
    antz
    -0.07
    æ´ĭ
    -0.07
    enj
    -0.06
    assistant
    -0.06
    åĽĽçº§
    -0.06
    çļĦçŁ¥è¯Ĩ
    -0.06
    jour
    -0.06
    razier
    -0.06
    çıij
    -0.06
    utie
    -0.06
    POSITIVE LOGITS
     inoltre
    0.08
    üy
    0.08
    udes
    0.07
     dunque
    0.07
    ón
    0.07
    ä¹ŁåĽłæѤ
    0.07
    ebin
    0.07
     natomiast
    0.07
     vesti
    0.07
    PRECATED
    0.07
    Activations Density 0.254%

    No Known Activations