© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17703
    Prev
    Next
    INDEX
    Explanations

    exercise or tutorial

    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
    åĮĹè·¯
    -0.08
    \V
    -0.08
    ÙħاÙĨ
    -0.07
    oure
    -0.07
    uzz
    -0.07
    åŃĺ
    -0.07
    łĢ
    -0.07
     stabil
    -0.07
    [selected
    -0.07
    稳å®ļ
    -0.07
    POSITIVE LOGITS
     physics
    0.07
    æĪijæĦ¿
    0.07
    ohan
    0.07
    çļĦè¿IJåĬ¨
    0.07
    çļĦèĩªçĶ±
    0.07
    oger
    0.07
     ÑĦизиÑĩеÑģкого
    0.06
    å¤ĩå¿ĺ
    0.06
    çī©çIJĨ
    0.06
     dun
    0.06
    Activations Density 0.026%

    No Known Activations