© 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. 19645
    Prev
    Next
    INDEX
    Explanations

    mechanical parts

    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
    ä¸įæĭĺ
    -0.07
     sense
    -0.07
     vall
    -0.06
    .Services
    -0.06
     dotted
    -0.06
    æĭŁå»º
    -0.06
    æģ°å¥½
    -0.06
     yet
    -0.06
    ugna
    -0.06
    åĪļ好
    -0.06
    POSITIVE LOGITS
     integrity
    0.10
     Integrity
    0.09
     vieill
    0.09
    å®Į好
    0.09
    åıĬ缸åħ³
    0.09
     دÚĨار
    0.09
    ernals
    0.08
    åıĬåIJĦ
    0.08
     ÑĨелоÑģÑĤ
    0.08
    -parts
    0.08
    Activations Density 0.135%

    No Known Activations