© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    Irish, Ali, japon, clip, Blue, McCabe, Regular

    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
    åīį款
    -0.09
    ouce
    -0.08
    ikian
    -0.07
    欢声
    -0.07
    ?,?,?,?,
    -0.07
    utsch
    -0.07
    ÃŃtulo
    -0.07
     suche
    -0.06
    åĽĽ
    -0.06
    çļĦäºĶ
    -0.06
    POSITIVE LOGITS
    ä¸īèĢħ
    0.24
    è¿Ļä¸ī
    0.23
    è¿Ļä¸ī个
    0.21
    è¿Ļä¸īç§į
    0.21
    ä¸ī人
    0.18
     Ketiga
    0.18
    ä¸īåľ°
    0.17
    ä¸īæĸ¹
    0.16
    ä¸īç§į
    0.16
    ä¸ī大
    0.16
    Activations Density 1.573%

    No Known Activations