© 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. 62485
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences or proofs

    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
    ippi
    -0.08
    áÄį
    -0.07
    ĤŃ
    -0.07
    elsey
    -0.07
    åı¸éķ¿
    -0.07
    äger
    -0.07
    åĶģ
    -0.07
     îng
    -0.06
    ago
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
    Ñīи
    0.07
    zinho
    0.06
    ersistent
    0.06
    æĸ°æĺŁ
    0.06
    念念ä¸įå¿ĺ
    0.06
    geb
    0.06
    Hat
    0.06
    ulia
    0.06
    OM
    0.06
    群éĽĦ
    0.06
    Activations Density 0.001%

    No Known Activations