© 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. 24128
    Prev
    Next
    INDEX
    Explanations

    adjacencies and neighbors

    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
    ptom
    -0.07
     cÃŃ
    -0.07
    oproject
    -0.07
    å¹¶ä½ľ
    -0.07
     Extras
    -0.07
    icar
    -0.06
    æĬ¥äºĨ
    -0.06
    language
    -0.06
    å½ĵäºĭ人çļĦ
    -0.06
     xá
    -0.06
    POSITIVE LOGITS
     neighbouring
    0.10
    ä¸ĭä¸Ģ
    0.10
     neighboring
    0.10
    缸éĤ»
    0.09
     neighbors
    0.09
    éĤ»å±ħ
    0.09
    Neighbor
    0.09
    Neighbors
    0.09
     adjacent
    0.09
    _neighbors
    0.09
    Activations Density 0.041%

    No Known Activations