© 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. 62040
    Prev
    Next
    INDEX
    Explanations

    a placeholder followed by a word

    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
    Fetcher
    -0.08
     lately
    -0.08
    lett
    -0.08
    åĪĨ享åĪ°
    -0.07
    lend
    -0.07
    å¿ĥä¸Ńæľīæķ°
    -0.07
    太大äºĨ
    -0.07
    æĶ«
    -0.06
    çīĪæĿĥå½Ĵ
    -0.06
    lø
    -0.06
    POSITIVE LOGITS
    èIJ
    0.08
    edig
    0.07
    maks
    0.07
    åĬªåĬĽå®ŀçİ°
    0.07
    å¹´æľŁ
    0.06
    åĩıå°ij对
    0.06
    bauer
    0.06
    åºĶæĮīçħ§
    0.06
    queira
    0.06
     maturity
    0.06
    Activations Density 0.002%

    No Known Activations