© 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. 25160
    Prev
    Next
    INDEX
    Explanations

    CD, relationship, wagon, machinery

    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
    IClient
    -0.06
    _CL
    -0.06
     käs
    -0.06
    åĺĽ
    -0.06
    .Fields
    -0.06
    å®ĺ宣
    -0.06
    åijĢ
    -0.06
    梧
    -0.06
     over
    -0.05
    éĩı身
    -0.05
    POSITIVE LOGITS
    ayne
    0.07
    pires
    0.07
    .dsl
    0.07
    bower
    0.07
     Borsa
    0.07
    ãģķãģ¾
    0.07
    ÌĢ
    0.07
    ontaine
    0.07
    éķ¿ä¹IJ
    0.07
    çī¹å¾µ
    0.07
    Activations Density 0.008%

    No Known Activations