© 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. 41537
    Prev
    Next
    INDEX
    Explanations

    email and mailbox systems

    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
     filmer
    -0.08
     SSR
    -0.08
    åĪ©çī©
    -0.08
    GetValue
    -0.07
    éĽªç³ķ
    -0.07
    vant
    -0.07
    ç¦ıç¦Ħ
    -0.07
     اÙĦØŃÙĥÙħ
    -0.07
     RVA
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    POSITIVE LOGITS
    æĶ¶ä»¶
    0.12
    éĤ®ä»¶
    0.11
     emails
    0.11
     mail
    0.11
    åıĹä¿¡
    0.11
     sender
    0.10
    éĢģä¿¡
    0.10
     mailbox
    0.10
    ĵ¨
    0.10
     recipient
    0.10
    Activations Density 0.360%

    No Known Activations