© 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. 43447
    Prev
    Next
    INDEX
    Explanations

    photo credit

    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
    ardino
    -0.08
    ardini
    -0.07
    å³¥åµĺ
    -0.07
    teman
    -0.07
    ÑħаÑħ
    -0.07
    avl
    -0.07
    quiv
    -0.07
    asser
    -0.07
    "https
    -0.07
    maal
    -0.07
    POSITIVE LOGITS
    çIJĨ
    0.07
    注æĦıçļĦæĺ¯
    0.06
    ovas
    0.06
    incu
    0.06
     DWORD
    0.06
    éri
    0.06
    ertain
    0.06
    Ùħت
    0.06
    åij½åIJį为
    0.06
     åt
    0.06
    Activations Density 0.340%

    No Known Activations