© 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. 47476
    Prev
    Next
    INDEX
    Explanations

    two of

    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
    æĭĽ
    -0.08
    agni
    -0.08
    edere
    -0.08
    æĹłä»»ä½ķ
    -0.07
    eder
    -0.07
    å±ķéĸĭ
    -0.07
    æĹ¢ä¸į
    -0.07
     neither
    -0.07
    enance
    -0.07
    cho
    -0.07
    POSITIVE LOGITS
    ä¸ī项
    0.08
    两项
    0.08
     ÙħتØŃد
    0.07
    Minor
    0.07
    è°ħ
    0.07
    èĢĮä¸İ
    0.07
     Sind
    0.07
    ùm
    0.07
    -thirds
    0.07
    esson
    0.07
    Activations Density 0.127%

    No Known Activations