© 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. 22368
    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¸Ģ个éĹ®é¢ĺ
    -0.08
    cea
    -0.08
    åıªåģļ
    -0.08
    夫æĸ¯åŁº
    -0.08
    asd
    -0.08
    ä¸Ģèµ·åģļ
    -0.08
    éĢ»
    -0.07
    körper
    -0.07
    为æѤ
    -0.07
    æĥ³åĪ°è¿ĻéĩĮ
    -0.07
    POSITIVE LOGITS
    ¼
    0.06
     table
    0.06
    scribe
    0.06
     S
    0.06
    ä¸įè¯Ĩ
    0.06
     forget
    0.06
     cor
    0.06
    åĨħå£ģ
    0.05
    intern
    0.05
    .tap
    0.05
    Activations Density 0.000%

    No Known Activations