© 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. 59776
    Prev
    Next
    INDEX
    Explanations

    configuration parameters

    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
    :boolean
    -0.08
    AndGet
    -0.07
    .Controllers
    -0.07
    :Boolean
    -0.07
    stract
    -0.07
    ehu
    -0.07
    cv
    -0.07
    æĸ¹å¼ı使çĶ¨
    -0.07
    루
    -0.07
    .offsetHeight
    -0.07
    POSITIVE LOGITS
    andom
    0.07
    ANDOM
    0.07
     =
    0.07
    çŁ³åĮĸ
    0.06
    åĹ£
    0.06
    ãĢģ“
    0.06
    âĢ¦âĢ¦
    0.06
     Madre
    0.06
    åĩ«
    0.06
    idden
    0.06
    Activations Density 0.269%

    No Known Activations