© 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. 8557
    Prev
    Next
    INDEX
    Explanations

    Squaring and methylation

    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
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
     Stephens
    -0.07
    axter
    -0.07
    jdk
    -0.07
    åī¯ä¼ļéķ¿
    -0.07
    rane
    -0.07
     Riccardo
    -0.07
    åĪĽåħĪ
    -0.07
    æľīæ°§
    -0.07
     Spinner
    -0.07
    POSITIVE LOGITS
    olate
    0.07
    æĿij
    0.06
    åĨĻä¿¡
    0.06
    æ²Ļ
    0.06
    ks
    0.06
    asto
    0.06
    AST
    0.06
    agin
    0.06
    asian
    0.06
    ailing
    0.06
    Activations Density 0.001%

    No Known Activations