© 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. 11373
    Prev
    Next
    INDEX
    Explanations

    destroying or tearing up

    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
    è¿Ļ次活åĬ¨
    -0.07
    æģ©
    -0.07
    enant
    -0.07
    åĿĢ
    -0.06
    æ°¸
    -0.06
    ä¸įä¿Ĺ
    -0.06
    çļĦåıĺåĮĸ
    -0.06
     gericht
    -0.06
    é«ĺ度çļĦ
    -0.06
    çĶŁåij½çļĦ
    -0.06
    POSITIVE LOGITS
     offending
    0.11
    æľ¬å°±
    0.08
    èĭ¦å¿ĥ
    0.08
    åİŁæľīçļĦ
    0.08
    ourse
    0.08
     bỼt
    0.08
    并å¤Ħ
    0.08
    æķıæĦŁçļĦ
    0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.08
     troublesome
    0.08
    Activations Density 0.220%

    No Known Activations