© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34925
    Prev
    Next
    INDEX
    Explanations

    overlapping concepts and structures

    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
    Negative Logits
    uggy
    -0.09
    icke
    -0.08
    ä¸į欲
    -0.07
    ITHER
    -0.07
    สัà¸Ļ
    -0.07
    haf
    -0.07
    erat
    -0.07
     convainc
    -0.07
    天ä¹ĭ
    -0.07
    ä»Ģ
    -0.07
    POSITIVE LOGITS
     overlapping
    0.13
     overlaps
    0.10
     overlap
    0.10
     interference
    0.10
    inter
    0.10
    缸äºĴ
    0.10
     interfere
    0.09
    äºĴ缸
    0.09
    å½¼æѤ
    0.09
    overlap
    0.09
    Activations Density 0.047%

    No Known Activations