© 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. 40224
    Prev
    Next
    INDEX
    Explanations

    preclusion, estoppel, death, judgment

    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
     riêng
    -0.07
     didik
    -0.07
     ervan
    -0.07
    fid
    -0.07
    亥
    -0.07
    çĿĢ头
    -0.07
    ãģ£ãģ·
    -0.07
    åı¯æĥ³
    -0.07
    ialis
    -0.07
    .setLevel
    -0.07
    POSITIVE LOGITS
    éĢĤçĶ¨
    0.07
    uin
    0.07
    ²
    0.07
    éĢĤçĶ¨çļĦ
    0.07
     applic
    0.07
    getContext
    0.06
     applicable
    0.06
    amis
    0.06
     Pino
    0.06
    جÙĪ
    0.06
    Activations Density 0.007%

    No Known Activations