© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    converting data or linking components

    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
    åĨįæĿ¥
    -0.07
    åŃ£åIJİ
    -0.07
    pires
    -0.07
    acci
    -0.07
    åłĤåłĤ
    -0.07
    ssen
    -0.07
    èĬ³èįī
    -0.07
    åĨħ容åıĬ
    -0.06
    æı
    -0.06
    aksi
    -0.06
    POSITIVE LOGITS
    转åĮĸ
    0.10
    conversion
    0.10
     conversion
    0.10
     converts
    0.09
    Conversion
    0.09
     converting
    0.09
     linking
    0.09
    转åĮĸçļĦ
    0.09
     Bridge
    0.09
     bridge
    0.09
    Activations Density 0.343%

    No Known Activations