© 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. 49189
    Prev
    Next
    INDEX
    Explanations

    code delimiters and syntax

    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
    ury
    -0.07
    äºī
    -0.07
    ensing
    -0.06
    çľĭéĩį
    -0.06
    å±Ī
    -0.06
    é¸
    -0.06
    ä¸īä¸Ģ
    -0.06
    ags
    -0.06
    éĶ¢
    -0.06
    ourse
    -0.06
    POSITIVE LOGITS
    วา
    0.08
    κÏģα
    0.07
    æľīä½ł
    0.07
    æł¸åıij
    0.07
    iggio
    0.07
    åħĭç¦ı
    0.07
    æŀ£
    0.07
    à¹Ģวียà¸Ļ
    0.07
    oare
    0.07
    æĻĥ
    0.07
    Activations Density 0.001%

    No Known Activations