© 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. 26909
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¹³åĿĩæ¯ı
    -0.09
    èĢĮå½Ĵ
    -0.07
    欢è¿İæĤ¨
    -0.07
    笳
    -0.07
    éħĴå±ĭ
    -0.07
    åĽŀé¦ĸ
    -0.07
    å®ŀéĻħæݧåĪ¶
    -0.07
    å¢ĥçļĦ
    -0.07
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.06
    ÑĤÑĮÑı
    -0.06
    POSITIVE LOGITS
    åħ³ç³»
    0.08
    åħ³ç³»ä¸Ń
    0.08
     Relationship
    0.07
    äºĴæį¢
    0.07
     relationship
    0.07
    Relationship
    0.07
    åĴĮä¸į足
    0.06
    arian
    0.06
    转æį¢
    0.06
    çļĦåħ³ç³»
    0.06
    Activations Density 0.000%

    No Known Activations