© 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. 30982
    Prev
    Next
    INDEX
    Explanations

    partitions

    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
    esor
    -0.08
    çī¢
    -0.07
    vog
    -0.07
    shiv
    -0.07
    åĬĽå£«
    -0.07
    acca
    -0.07
     nami
    -0.07
    LECT
    -0.06
    _multip
    -0.06
    被迫
    -0.06
    POSITIVE LOGITS
    ä¼ļåIJĮ
    0.07
    atsu
    0.07
    ¤íĶ
    0.06
    quil
    0.06
    hte
    0.06
    htë
    0.06
    ÃŃž
    0.06
    elin
    0.06
    ipt
    0.06
     byteArray
    0.06
    Activations Density 0.011%

    No Known Activations