© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    get;

    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
    well
    -0.07
    åįİ侨
    -0.07
    涵åħ»
    -0.07
    åĪĻ表示
    -0.06
    ermann
    -0.06
    ilder
    -0.06
    æģĭ
    -0.06
     accum
    -0.06
    سÙĦاÙħ
    -0.06
    å¾Ī好å¥ĩ
    -0.06
    POSITIVE LOGITS
    ÎŃÏģγ
    0.08
     Zut
    0.07
    stående
    0.07
    нев
    0.07
    æĨ¬
    0.07
    åĪĺæĸĩ
    0.07
    Įĵ
    0.07
    èĬĻ
    0.07
    ******/
    0.07
    קר
    0.07
    Activations Density 0.006%

    No Known Activations