© 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. 32230
    Prev
    Next
    INDEX
    Explanations

    ammonium compounds

    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
    lessly
    -0.08
    ียà¸Ķ
    -0.07
    walt
    -0.07
    åij½ä¸Ń
    -0.07
    abet
    -0.07
    erei
    -0.07
    minat
    -0.07
    erman
    -0.07
    -même
    -0.07
    åĿĬ
    -0.07
    POSITIVE LOGITS
    大åıĶ
    0.08
    inine
    0.07
    oise
    0.07
    צ×Ļ
    0.07
    à¹Ħ
    0.07
    æł¼éĩĮ
    0.07
     Icelandic
    0.07
    zinho
    0.06
    éĺ¿å§¨
    0.06
    lepas
    0.06
    Activations Density 0.007%

    No Known Activations