© 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. 22373
    Prev
    Next
    INDEX
    Explanations

    coding syntax and variables

    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
    çŃij
    -0.06
    对åĨħ
    -0.06
    unicode
    -0.06
    ame
    -0.06
     target
    -0.06
    ä¸Ńéĥ¨
    -0.06
    çĶ³
    -0.06
     vá»±c
    -0.06
    建
    -0.06
    eric
    -0.06
    POSITIVE LOGITS
     Decay
    0.10
    æĤĶ
    0.08
    olland
    0.08
     decay
    0.08
    StateManager
    0.08
    ivor
    0.08
    _executor
    0.08
    decay
    0.08
    åĦ¿æŶ
    0.08
    etje
    0.08
    Activations Density 0.002%

    No Known Activations