© 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. 32405
    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
    æľĪ份å¼Ģå§ĭ
    -0.08
    onde
    -0.08
    urig
    -0.07
    çī§
    -0.07
    ä¸ŃæĭĽ
    -0.07
    ADING
    -0.07
    æħķå°¼
    -0.07
    è§ĦåĪĴå±Ģ
    -0.07
    ugi
    -0.07
    åĿļæĮģä¸ĭåİ»
    -0.07
    POSITIVE LOGITS
    decoder
    0.07
    каÑĥ
    0.07
    åįļè§Ī
    0.07
     consol
    0.07
     маÑģÑĤ
    0.07
    ikk
    0.07
     gand
    0.06
    chunk
    0.06
    éĺ
    0.06
    以æѤ
    0.06
    Activations Density 0.000%

    No Known Activations