© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18259
    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
     Mist
    -0.07
     mist
    -0.07
    æĻķ
    -0.07
    ekin
    -0.06
     Pride
    -0.06
    rt
    -0.06
    人家
    -0.06
     Bought
    -0.06
    å°Ķé¡¿
    -0.06
    çĶµéĩı
    -0.06
    POSITIVE LOGITS
    éģĩäºĭ
    0.08
    åıĤåĬłæ¯ĶèµĽ
    0.07
    æĪIJ绩çļĦ
    0.07
    umeric
    0.07
    yper
    0.07
    dden
    0.07
    ulli
    0.07
    ierno
    0.07
    å¾¹
    0.07
    gil
    0.07
    Activations Density 0.000%

    No Known Activations