© 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. 31094
    Prev
    Next
    INDEX
    Explanations

    indices of measurement

    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
    yu
    -0.07
    ãĥ«ãĥķ
    -0.07
    ×IJ×Ļ
    -0.07
    vido
    -0.07
    ковод
    -0.07
    uman
    -0.07
    ongyang
    -0.06
    rick
    -0.06
    ijing
    -0.06
    ä¸Ŀä¸Ŀ
    -0.06
    POSITIVE LOGITS
    åįıåĬŀ
    0.07
    驶
    0.07
    ewear
    0.06
    -settings
    0.06
    orti
    0.06
    çħľ
    0.06
    缸çĪ±
    0.06
    ossi
    0.06
    lee
    0.06
    eden
    0.06
    Activations Density 1.654%

    No Known Activations