© 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. 57249
    Prev
    Next
    INDEX
    Explanations

    national, attribution, identification

    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
    åĬłæĭ¿å¤§
    -0.07
    dings
    -0.07
    ###
    -0.07
    wap
    -0.07
    大家ä¸Ģèµ·
    -0.07
    Ùħا
    -0.07
    cht
    -0.07
    ouc
    -0.07
    cala
    -0.07
    lop
    -0.06
    POSITIVE LOGITS
    umer
    0.08
    sb
    0.08
    sy
    0.07
    ible
    0.07
    ification
    0.07
    iele
    0.07
    iest
    0.07
    ional
    0.07
    ycl
    0.07
    à¥Ģ
    0.07
    Activations Density 0.678%

    No Known Activations