© 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. 25968
    Prev
    Next
    INDEX
    Explanations

    chicken, nurse, boy, hallway, couple, soccer, sweet, ore, poems, assignment

    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
    ```
    -0.06
    åIJįåĪ©
    -0.06
    “
    -0.05
    æ¸ħæĺİ
    -0.05
    ill
    -0.05
    é¦ĸåħĪ
    -0.05
    [(
    -0.05
    [
    -0.05
    çľĭä¾Ĩ
    -0.05
     elusive
    -0.05
    POSITIVE LOGITS
    uite
    0.08
    BTN
    0.08
    uit
    0.08
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    丹丹
    0.08
    peed
    0.08
    uid
    0.08
    Ngu
    0.08
    份åŃIJ
    0.08
    çİ°çĬ¶åıĬ
    0.08
    Activations Density 0.008%

    No Known Activations