© 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. 61654
    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
    baran
    -0.08
    ç½ijæł¡
    -0.08
    }@
    -0.08
    æĭīå¼Ģ
    -0.08
    avin
    -0.08
    ourcem
    -0.07
    issé
    -0.07
    ibun
    -0.07
    社ä¼ļä¿¡çĶ¨ä»£çłģ
    -0.07
    Ľ
    -0.07
    POSITIVE LOGITS
    izzy
    0.07
    bid
    0.06
    åİŁ
    0.06
    univers
    0.06
    è¿ĩåİ»
    0.06
    kel
    0.06
     punt
    0.06
    ãģij
    0.06
    pair
    0.06
    ä¸Ĭåİ»
    0.06
    Activations Density 0.000%

    No Known Activations