© 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. 37678
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    å¥Ķ
    -0.06
    za
    -0.06
    åĮª
    -0.06
    edar
    -0.06
    mee
    -0.06
    án
    -0.06
    edo
    -0.06
    anyi
    -0.06
    大夫
    -0.06
    éĶĭ
    -0.06
    POSITIVE LOGITS
    estos
    0.09
    å¦Ŀ
    0.08
     nenh
    0.08
    ãģĭãģķ
    0.08
    建çŃijè£ħ饰
    0.08
    udiant
    0.08
     erotisch
    0.07
    ensex
    0.07
    isodes
    0.07
    èµ·è§ģ
    0.07
    Activations Density 0.001%

    No Known Activations