© 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. 63181
    Prev
    Next
    INDEX
    Explanations

    black hole mass

    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
    家æĺ¯
    -0.07
    ylvania
    -0.07
    åĽ½æ°ij
    -0.07
    ÙĪجة
    -0.07
    èľľèľĤ
    -0.07
    .raise
    -0.07
    ĻĤ
    -0.06
    éĹº
    -0.06
    篷
    -0.06
    èİ
    -0.06
    POSITIVE LOGITS
    siz
    0.08
    乳头
    0.08
    igar
    0.08
    urch
    0.08
    ä¼ijçľł
    0.08
    å·¨åŀĭ
    0.07
    εδ
    0.07
    ÑĥÑĤа
    0.07
    cus
    0.07
    è¶ħ大
    0.07
    Activations Density 0.007%

    No Known Activations