© 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. 14774
    Prev
    Next
    INDEX
    Explanations

    using combined

    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
    amma
    -0.09
    ä¸ĸå¤ĸ
    -0.09
    å¥Īä½ķ
    -0.08
    lesia
    -0.08
    aan
    -0.08
    owler
    -0.08
    anen
    -0.08
    stad
    -0.08
    azos
    -0.08
    vist
    -0.08
    POSITIVE LOGITS
    åħ³ç³»
    0.07
    注åĨĮä¼ļåijĺ
    0.06
    uger
    0.06
     hil
    0.05
     relationship
    0.05
    æľ¬èº«
    0.05
    losure
    0.05
    ersed
    0.05
    åħ³äºĨ
    0.05
    reo
    0.05
    Activations Density 0.053%

    No Known Activations