© 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. 20129
    Prev
    Next
    INDEX
    Explanations

    rare earth elements

    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
    çİĭéģĵ
    -0.07
    ¢
    -0.07
    hear
    -0.07
    æ¤Ĵ
    -0.07
     dâu
    -0.07
     Adelaide
    -0.07
    amba
    -0.06
    é»į
    -0.06
     Aviv
    -0.06
     Rosenberg
    -0.06
    POSITIVE LOGITS
    ç¨ĢåľŁ
    0.09
    æ°¸ç£ģ
    0.08
    ç´«éĩij
    0.07
    unate
    0.07
    esium
    0.07
    aced
    0.07
     nord
    0.07
    esia
    0.07
    æĹłæŀģ
    0.07
     valer
    0.07
    Activations Density 0.029%

    No Known Activations