© 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. 22282
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    -0.07
    ennie
    -0.06
    rano
    -0.06
    ↵
    -0.06
    iglio
    -0.06
    agi
    -0.06
    ér
    -0.05
    oc
    -0.05
    **
    -0.05
    ire
    -0.05
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.10
     etc
    0.10
    etc
    0.10
    æĥħåĨµçŃī
    0.10
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.10
    翼翼
    0.09
     поздÑĢа
    0.09
     alike
    0.09
    åħ¶ä»ĸçļĦ
    0.09
     seterusnya
    0.09
    Activations Density 0.128%

    No Known Activations