© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39412
    Prev
    Next
    INDEX
    Explanations

    relations relationships

    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
    æ¡£
    -0.07
    ÙĪدÙĩ
    -0.06
    导
    -0.06
    窥
    -0.06
    éŃĶåĬĽ
    -0.06
    annen
    -0.06
    å¿ı
    -0.06
    Comm
    -0.06
    avan
    -0.06
    æĦŁæŁĵèĢħ
    -0.06
    POSITIVE LOGITS
    åħ³ç³»
    0.11
    åħ³ç³»ä¸Ń
    0.10
     relations
    0.10
     relationships
    0.10
     relationship
    0.10
     relation
    0.10
    åħ³ç³»çļĦ
    0.10
    éĹľç³»
    0.10
    ãģ®éĸ¢ä¿Ĥ
    0.10
    éĹľä¿Ĥ
    0.10
    Activations Density 0.003%

    No Known Activations