© 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. 34283
    Prev
    Next
    INDEX
    Explanations

    step

    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
    تÙĨا
    -0.10
     _:
    -0.10
    __:
    -0.09
    hre
    -0.09
    ttp
    -0.09
     }:
    -0.09
    ()):
    -0.09
    utan
    -0.09
    Abst
    -0.08
     ):
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
    ,
    0.07
    inqu
    0.06
    ç¡®å®ļ
    0.06
     understanding
    0.06
    æĺİç¡®
    0.06
    unsch
    0.06
     clearly
    0.06
    åĩĨå¤ĩ
    0.06
      ↵
    0.06
    Activations Density 0.003%

    No Known Activations