© 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. 43706
    Prev
    Next
    INDEX
    Explanations

    code punctuation symbols

    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
    éĤĥ
    -0.07
    åĨī
    -0.07
    ÙĪرÙĥ
    -0.07
    çļĦåİŁçIJĨ
    -0.06
    DEX
    -0.06
     precaution
    -0.06
    ;;;;;;;;
    -0.06
    oue
    -0.06
     Equipo
    -0.06
    ensa
    -0.06
    POSITIVE LOGITS
    garan
    0.07
    æĤłä¹ħçļĦ
    0.07
    妻
    0.07
    äºīåģļ
    0.07
    ãĤ¬ãĥ¼
    0.07
    agni
    0.07
    udin
    0.07
    åĺĨ
    0.07
    åı¹
    0.07
    aneous
    0.07
    Activations Density 0.001%

    No Known Activations