© 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. 42917
    Prev
    Next
    INDEX
    Explanations

    fractions and division operations

    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
    æk
    -0.08
    ãģĭãĤĭ
    -0.07
    uer
    -0.07
    atif
    -0.07
    chtig
    -0.07
    ake
    -0.07
    emar
    -0.07
    æī§çħ§
    -0.07
     prioritize
    -0.07
    ixon
    -0.07
    POSITIVE LOGITS
    iders
    0.07
    åĬŀåħ¬å®¤ä¸»ä»»
    0.07
    li
    0.07
    unid
    0.07
    stride
    0.07
    ç·»
    0.06
    è··
    0.06
    .documentation
    0.06
    -eff
    0.06
    ensa
    0.06
    Activations Density 0.004%

    No Known Activations