© 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. 56099
    Prev
    Next
    INDEX
    Explanations

    modulo operations and string 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
     Probe
    -0.07
    åĨł
    -0.07
    abis
    -0.06
    æłĵ
    -0.06
    ully
    -0.06
    å¾ħ
    -0.06
    clare
    -0.06
    Zum
    -0.06
    èĥľ
    -0.06
    åĭĿ
    -0.06
    POSITIVE LOGITS
    åĦĢ
    0.08
     Cities
    0.08
    æĿŁ
    0.08
    dock
    0.07
     ìŬ
    0.07
    еÑģÑģи
    0.07
    æĥħæľī
    0.07
     bø
    0.07
    .LEFT
    0.07
    ItemCount
    0.07
    Activations Density 0.001%

    No Known Activations