© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    section titles and answers

    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
    eyer
    -0.08
    æ³¾
    -0.08
    好礼
    -0.08
    URRENT
    -0.08
    toInt
    -0.08
    oeff
    -0.08
    witter
    -0.08
    theless
    -0.08
     Hemisphere
    -0.07
    ergestellt
    -0.07
    POSITIVE LOGITS
     super
    0.07
    hut
    0.06
    ule
    0.06
     stew
    0.06
    æĢģ度åĴĮ
    0.06
    fen
    0.06
     thorough
    0.06
    chau
    0.06
    vv
    0.05
     v
    0.05
    Activations Density 0.007%

    No Known Activations