© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    nitrogen and chemical structures

    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
    gang
    -0.09
    eur
    -0.08
    å¾·éŁ³
    -0.08
    ivity
    -0.07
    iby
    -0.07
    å¬ī
    -0.07
    zeitig
    -0.07
    øl
    -0.07
    erre
    -0.07
    ffe
    -0.07
    POSITIVE LOGITS
     dioxide
    0.10
    عت
    0.10
    åijIJ
    0.09
    oodle
    0.08
    ucle
    0.08
    exus
    0.08
    ighth
    0.08
    оÑı
    0.08
    onsense
    0.08
    ovo
    0.08
    Activations Density 0.038%

    No Known Activations