© 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. 28322
    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
    arme
    -0.07
    å°Ķ夫
    -0.07
    å¾Īå¤ļæľĭåıĭ
    -0.07
    .nd
    -0.07
    iter
    -0.06
    Ả
    -0.06
    ä¸Ģ个女人
    -0.06
    пам
    -0.06
    anit
    -0.06
     undertaking
    -0.06
    POSITIVE LOGITS
    κÎŃ
    0.07
    ł
    0.07
    ণ
    0.06
    inality
    0.06
    abila
    0.06
    ãģ«è¦ĭ
    0.06
    phins
    0.06
    请åıĤèĢĥ
    0.06
     Generated
    0.06
    eness
    0.06
    Activations Density 0.000%

    No Known Activations