© 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. 62358
    Prev
    Next
    INDEX
    Explanations

    matte black, winter wedding, pathological gambling

    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
    ex
    -0.06
    åĽŀ
    -0.06
    rons
    -0.05
    was
    -0.05
    éĽĦ
    -0.05
      ↵
    -0.05
    3
    -0.05
    ä¼ij
    -0.05
     fond
    -0.05
    ikko
    -0.05
    POSITIVE LOGITS
    ubin
    0.10
    оÑĤÑĢе
    0.09
    转载æĪĸå¼ķçĶ¨
    0.08
    ãģĵãĤĮãĤĤ
    0.08
    acie
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.08
    ceb
    0.08
    ¶
    0.08
    UpdatedAt
    0.08
    peen
    0.08
    Activations Density 0.027%

    No Known Activations