© 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. 21958
    Prev
    Next
    INDEX
    Explanations

    logical inconsistencies or exceptions

    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
    sockets
    -0.08
    új
    -0.08
    esco
    -0.08
    سÙĪ
    -0.08
    wich
    -0.08
    _recursive
    -0.08
    uild
    -0.07
    য়à§ĩ
    -0.07
    aths
    -0.07
    esas
    -0.07
    POSITIVE LOGITS
     sequer
    0.08
    kopf
    0.07
    éŀ
    0.06
    kert
    0.06
    åı¯çŁ¥
    0.06
     kn
    0.06
     اÛĮÙĨÚ©Ùĩ
    0.06
    å·²æĺ¯
    0.06
    è±
    0.06
     sustained
    0.06
    Activations Density 0.003%

    No Known Activations