© 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. 30363
    Prev
    Next
    INDEX
    Explanations

    genre, developer, language, species

    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
    å¼Ģ好
    -0.07
    仿
    -0.06
     Spek
    -0.06
    jih
    -0.06
    _DS
    -0.06
    esser
    -0.06
    ç½ijå°ıç¼ĸ
    -0.06
    ito
    -0.06
    azon
    -0.06
    ãĤıãģĸ
    -0.06
    POSITIVE LOGITS
    ieger
    0.08
    ourt
    0.08
    engar
    0.08
    uger
    0.08
    åħ³æ³¨æĪij们
    0.08
    estand
    0.08
    anager
    0.07
    ategoria
    0.07
    ousel
    0.07
     siehe
    0.07
    Activations Density 0.172%

    No Known Activations