© 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. 13448
    Prev
    Next
    INDEX
    Explanations

    python code and commands

    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
     Gas
    -0.08
    æĹłéĹ´
    -0.08
    á»ĵ
    -0.07
     Palma
    -0.07
    shift
    -0.07
    Gas
    -0.07
    æľīå¥ĸ
    -0.07
    æݨæĭī
    -0.07
    -bre
    -0.07
     mam
    -0.07
    POSITIVE LOGITS
    .python
    0.11
     setuptools
    0.09
    Python
    0.09
     Django
    0.09
     Python
    0.09
    PYTHON
    0.08
    python
    0.08
     python
    0.08
     django
    0.08
     PYTHON
    0.08
    Activations Density 0.285%

    No Known Activations