© 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. 49545
    Prev
    Next
    INDEX
    Explanations

    career|personnel|people|program|external|warning

    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
     Crosby
    -0.07
    uf
    -0.07
     Bianco
    -0.06
    ourg
    -0.06
    ses
    -0.06
    uff
    -0.06
    æĦıæĢĿ
    -0.06
    uffs
    -0.06
     suffice
    -0.06
    æĦıæĢĿæĺ¯
    -0.06
    POSITIVE LOGITS
    anko
    0.08
    寧
    0.08
    åijĬè¯īèĩªå·±
    0.07
    berat
    0.07
    飶åįİ
    0.07
    Works
    0.07
     rumored
    0.06
     Sword
    0.06
     alternative
    0.06
    ä»ij
    0.06
    Activations Density 0.001%

    No Known Activations