© 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. 22083
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or symbols

    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
    wards
    -0.09
    çļĦæĺ¯ä»Ģä¹Ī
    -0.08
     entirety
    -0.07
    è¯ķé¢ĺ
    -0.07
    /Edit
    -0.07
    izable
    -0.07
    chemist
    -0.07
    åİĤçļĦ
    -0.07
    lichten
    -0.07
    ybrid
    -0.07
    POSITIVE LOGITS
    身临åħ¶å¢ĥ
    0.08
    nbsp
    0.08
    orary
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    ↵
    0.07
    èĢ³çĨŁèĥ½è¯¦
    0.07
    à¸ģาร
    0.07
    çī¹çĤ¹æĺ¯
    0.07
    аÑĤо
    0.07
    outh
    0.06
    Activations Density 0.001%

    No Known Activations