© 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. 58044
    Prev
    Next
    INDEX
    Explanations

    geometric and descriptive properties

    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
    èįŁ
    -0.07
    rones
    -0.06
    boten
    -0.06
     Sido
    -0.06
     inde
    -0.06
    mons
    -0.06
     prospective
    -0.06
    hait
    -0.06
    约è°Ī
    -0.06
     Pearl
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮ导èĩ´
    0.10
     ÙĪباÙĦتاÙĦÙĬ
    0.09
    å¼ķèµ·çļĦ
    0.08
    ä»İèĢĮ
    0.08
    å¤Ħ以
    0.08
    å¼ķèµ·
    0.08
     genug
    0.08
     sehingga
    0.08
    å¤Ħ
    0.08
     Dadurch
    0.08
    Activations Density 0.277%

    No Known Activations