© 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. 24106
    Prev
    Next
    INDEX
    Explanations

    exclamations followed by punctuation

    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
    ufs
    -0.07
    ini
    -0.07
    æĹłèĻij
    -0.07
    átk
    -0.07
     Threat
    -0.07
    é«ĺ度
    -0.07
    âl
    -0.06
    threat
    -0.06
    ikt
    -0.06
    permalink
    -0.06
    POSITIVE LOGITS
    éĶ¦æłĩ
    0.07
    alez
    0.07
    !important
    0.07
    妩
    0.07
    _categorical
    0.07
    注æĦıäºĨ
    0.07
     Eure
    0.07
    ostas
    0.06
    estas
    0.06
    èİĺ
    0.06
    Activations Density 0.004%

    No Known Activations