© 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. 20922
    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
    atment
    -0.08
    amil
    -0.08
    guna
    -0.08
    μÏĢ
    -0.08
    vana
    -0.08
    ÙħاÙħ
    -0.08
    çĤ¹ä¸ªèµŀ
    -0.08
    ÃŃo
    -0.08
    bage
    -0.08
    fds
    -0.08
    POSITIVE LOGITS
    ↵↵
    0.07
    ,
    0.07
    :
    0.07
    许å¤ļ
    0.07
    åıªéľĢ
    0.07
    ä¸Ģ个
    0.07
    ¼
    0.07
    åıªè¦ģ
    0.06
    _
    0.06
    __
    0.06
    Activations Density 0.000%

    No Known Activations