© 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. 45693
    Prev
    Next
    INDEX
    Explanations

    convergent, parallel, independent, similar

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    交代
    -0.08
    ķĮ
    -0.08
    åĮºåĪĨ
    -0.08
    ermann
    -0.07
    eries
    -0.07
    åĪĨæ¸ħ
    -0.07
    FINE
    -0.07
    ukan
    -0.07
    rvine
    -0.07
    AFX
    -0.07
    POSITIVE LOGITS
    å·§åIJĪ
    0.15
    çĽ¸ä¼¼çļĦ
    0.15
    çĽ¸ä¼¼
    0.14
     similar
    0.13
    类似çļĦ
    0.13
     ÑģÑħо
    0.12
     ähnliche
    0.12
     coinc
    0.12
    鼷åIJĮ
    0.12
    类似
    0.11
    Activations Density 0.225%

    No Known Activations