© 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. 40959
    Prev
    Next
    INDEX
    Explanations

    concatenations and contributions

    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
    ä¸įå®ļ
    -0.07
    fil
    -0.07
    å»
    -0.07
    åľ
    -0.07
     junior
    -0.06
     scr
    -0.06
    _header
    -0.06
    Accessor
    -0.06
    ä¸ĭåľº
    -0.06
    å¤ķ
    -0.06
    POSITIVE LOGITS
     concaten
    0.11
    è´¡çĮ®
    0.10
    åIJĪ并
    0.10
     contributions
    0.10
     Contributions
    0.10
     concatenate
    0.10
    åıłåĬł
    0.09
    è²¢çį»
    0.09
     contribution
    0.09
     기ìŬ
    0.09
    Activations Density 0.083%

    No Known Activations