© 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. 20772
    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
    ondi
    -0.08
    çĤľ
    -0.08
    æĻŁ
    -0.08
     supon
    -0.08
    ábado
    -0.08
    ÙĤاض
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    mega
    -0.07
     Fino
    -0.07
    æīĢè°ĵ
    -0.07
    POSITIVE LOGITS
     repeatedly
    0.06
     associative
    0.06
     res
    0.06
    åĪ°ä¸ŃåĽ½
    0.06
     significantly
    0.06
    çī
    0.06
    }
    0.06
    ÙĬØ©
    0.06
    åĪ°å°¾
    0.06
     followed
    0.06
    Activations Density 0.000%

    No Known Activations