© 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. 35069
    Prev
    Next
    INDEX
    Explanations

    asian, asteroid, names

    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
    avings
    -0.08
    çİ®
    -0.08
     seputar
    -0.08
    elpers
    -0.08
    OrCreate
    -0.08
    abora
    -0.07
    anske
    -0.07
    ologe
    -0.07
    asst
    -0.07
    éĩĩ纳çİĩ
    -0.07
    POSITIVE LOGITS
    ãģĭãģ¤
    0.08
    ãģĤãģ£ãģ¦
    0.08
    +
    0.07
    å¨ģ
    0.07
    ³
    0.06
    ++,
    0.06
    ãĢģ“
    0.06
    +,
    0.06
    èĢĮä¸Ķæĺ¯
    0.06
    çŃīå¤ļ项
    0.06
    Activations Density 0.200%

    No Known Activations