© 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. 48880
    Prev
    Next
    INDEX
    Explanations

    spatial and temporal descriptors

    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
    anden
    -0.08
    eton
    -0.08
    è®
    -0.07
    å½¢å¼ı
    -0.07
     absent
    -0.07
    AGO
    -0.07
    ildo
    -0.07
    ÙĦاÙĦ
    -0.07
    Absent
    -0.07
    биÑĤÑĮ
    -0.07
    POSITIVE LOGITS
    æŃ£å¤Ħäºİ
    0.08
    ırı
    0.08
    æľĿ
    0.08
     Sele
    0.08
    alez
    0.08
    ìĹ½
    0.07
    临åºĬç»ıéªĮ
    0.07
    odin
    0.07
    .atom
    0.07
    åĪĪ
    0.07
    Activations Density 0.147%

    No Known Activations