© 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. 34238
    Prev
    Next
    INDEX
    Explanations

    code snippets and text formatting

    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
    åī¯åİ¿éķ¿
    -0.08
    Weit
    -0.08
     :(
    -0.08
    çݯä¿Ŀå±Ģ
    -0.08
    mern
    -0.07
    åįī
    -0.07
    صÙĪر
    -0.07
    hammer
    -0.07
    åݿ人
    -0.07
     Doma
    -0.07
    POSITIVE LOGITS
    ä¿®å¤į
    0.08
    .Protocol
    0.07
     unchanged
    0.06
    念
    0.06
    çħ§
    0.06
    åİŁæĸĩ
    0.06
    imd
    0.06
    astas
    0.06
    åİŁ
    0.06
     original
    0.06
    Activations Density 0.015%

    No Known Activations