© 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. 43803
    Prev
    Next
    INDEX
    Explanations

    detecting problems

    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
    缸åħ³éĹ®çŃĶ
    -0.08
    ãģıãĤĬ
    -0.07
    ç´§è·Ł
    -0.07
    ukai
    -0.07
    ä¸ŃçļĦåľ°ä½į
    -0.07
    odem
    -0.06
    erializer
    -0.06
    wt
    -0.06
    oya
    -0.06
    许å¤ļ
    -0.06
    POSITIVE LOGITS
    并åıĬæŶ
    0.10
    并æıIJåĩº
    0.10
    ä¸Ģ缮äºĨçĦ¶
    0.09
     évent
    0.09
     detected
    0.09
     Detected
    0.09
    端åĢª
    0.08
    çŃīä¸įèī¯
    0.08
    èĭĹ
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
    Activations Density 0.112%

    No Known Activations