© 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. 12107
    Prev
    Next
    INDEX
    Explanations

    invention mutations

    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
    ãĥ¼ãĥķ
    -0.09
     Spurs
    -0.08
    zak
    -0.08
    ÃģC
    -0.08
    zal
    -0.08
     seedu
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    ary
    -0.08
     Fá
    -0.08
    ayout
    -0.08
    POSITIVE LOGITS
    oland
    0.08
    o
    0.08
    uen
    0.06
    "
    0.06
    æľī家
    0.06
    oli
    0.06
    æĹ¥æĹ¥
    0.05
    ÙĬاء
    0.05
     Refuge
    0.05
    furt
    0.05
    Activations Density 0.001%

    No Known Activations