© 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. 56799
    Prev
    Next
    INDEX
    Explanations

    III-nitride materials

    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
    pty
    -0.07
    æŃ£æĸ¹
    -0.07
    .inputs
    -0.07
     Bronx
    -0.07
    æ´»
    -0.07
    éĨ
    -0.06
    æ¾³éŨ
    -0.06
    saf
    -0.06
    link
    -0.06
    çĽij
    -0.06
    POSITIVE LOGITS
    uhl
    0.10
    ä½ĵèĤ²ä¸Ńå¿ĥ
    0.09
    oggio
    0.08
    .vue
    0.08
    ä¼¸çĽ´
    0.07
    /rfc
    0.07
    à¸ĺาà¸ķุ
    0.07
    oday
    0.07
    ihen
    0.07
    awah
    0.07
    Activations Density 0.005%

    No Known Activations