© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29283
    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
     ÑģведениÑı
    -0.07
    纵横
    -0.07
    istle
    -0.06
    åĺ¶
    -0.06
     overriding
    -0.06
     either
    -0.06
    ä¸īçĻ¾
    -0.06
    unsafe
    -0.06
    å¡ĺéķĩ
    -0.06
    duct
    -0.06
    POSITIVE LOGITS
    egger
    0.09
    Advertising
    0.07
     trainable
    0.07
    ansch
    0.07
    ãi
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
     outputs
    0.07
    eiro
    0.07
     GLenum
    0.07
    urez
    0.07
    Activations Density 0.000%

    No Known Activations