© 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. 65098
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words

    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
    å±Ĥ
    -0.07
    .Utilities
    -0.07
     unf
    -0.07
    eras
    -0.07
    ινÏĮ
    -0.07
    eder
    -0.06
    ör
    -0.06
    endis
    -0.06
    æŦ
    -0.06
     taas
    -0.06
    POSITIVE LOGITS
    fx
    0.09
    _INCLUDED
    0.08
    骨头
    0.07
    )||(
    0.07
    aute
    0.07
    æħij
    0.07
    orme
    0.07
    ripper
    0.07
    hart
    0.07
    lair
    0.07
    Activations Density 0.001%

    No Known Activations