© 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. 32391
    Prev
    Next
    INDEX
    Explanations

    seed plants, $p^n$

    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
    ocks
    -0.07
    ë§ī
    -0.07
    ertext
    -0.06
    é»į
    -0.06
    ambang
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    /opt
    -0.06
    çIJĽ
    -0.06
     fine
    -0.06
    é«ĺä½İ
    -0.06
    POSITIVE LOGITS
    .Async
    0.08
    åħī大
    0.08
    teroid
    0.07
    omie
    0.07
    _Format
    0.07
    _INCREMENT
    0.07
    éĥ¨çº§
    0.07
    iled
    0.07
     progression
    0.07
     Kelley
    0.07
    Activations Density 0.002%

    No Known Activations