© 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. 35075
    Prev
    Next
    INDEX
    Explanations

    relationship

    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
    åħ¬å¹³ç«ŀäºī
    -0.08
    åħ¬å¹³åħ¬æŃ£
    -0.08
    åħ¬å¹³çļĦ
    -0.08
    åĩºèº«çļĦ
    -0.07
    ardin
    -0.07
    alti
    -0.07
    שת
    -0.07
    μή
    -0.07
    åħ¬å¹³
    -0.07
    Ø®ÙĨ
    -0.07
    POSITIVE LOGITS
    åħ³ç³»
    0.12
     relationship
    0.12
    åħ³ç³»ä¸Ń
    0.10
     Relationship
    0.10
     relationships
    0.10
    relationship
    0.10
    åħ³ç³»çļĦ
    0.10
    çļĦåħ³ç³»
    0.09
     Relationships
    0.09
    åĢį
    0.09
    Activations Density 0.004%

    No Known Activations