© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11155
    Prev
    Next
    INDEX
    Explanations

    numerical sequences before equals

    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
    éľĦ
    -0.07
     outright
    -0.07
    sert
    -0.07
    erver
    -0.07
    airo
    -0.07
    orar
    -0.07
    çĶļèĩ³æľīäºĽ
    -0.07
    agra
    -0.07
    è¿ijå¹³
    -0.07
    exas
    -0.06
    POSITIVE LOGITS
    buch
    0.07
    leting
    0.07
    沫
    0.07
    eneur
    0.07
    isial
    0.06
    deaux
    0.06
    åıĮ缮
    0.06
    Partial
    0.06
    IODevice
    0.06
    ebet
    0.06
    Activations Density 0.029%

    No Known Activations