© 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. 37587
    Prev
    Next
    INDEX
    Explanations

    placeholder for something

    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
     zarówno
    -0.08
     поне
    -0.08
    åij³çĶĺ
    -0.08
    aturi
    -0.07
    æѦç¥ŀ
    -0.07
    大åı¯
    -0.07
    äºĭåįĬåĬŁåĢį
    -0.07
     INLINE
    -0.07
    à¸Ļ
    -0.07
    DECL
    -0.07
    POSITIVE LOGITS
    ente
    0.07
    اء
    0.06
    ota
    0.06
    entifier
    0.06
     iota
    0.06
    zahl
    0.06
     krat
    0.06
    anz
    0.06
    quam
    0.06
    ou
    0.06
    Activations Density 0.007%

    No Known Activations