© 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. 39389
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä»ĺ诸
    -0.08
    ijs
    -0.08
    hir
    -0.08
    elry
    -0.08
    å°ĶåŁº
    -0.08
    luss
    -0.08
    oice
    -0.08
    éĵģé¾Ļ
    -0.08
    omor
    -0.08
    ä¹ĭæ°´
    -0.07
    POSITIVE LOGITS
     h
    0.07
    OTE
    0.07
     bree
    0.06
    ople
    0.06
    åĪ¶èį¯
    0.06
     dura
    0.06
    çŃĶçĸij解æĥij
    0.06
     v
    0.06
    0.06
    eric
    0.06
    Activations Density 0.000%

    No Known Activations