© 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. 55876
    Prev
    Next
    INDEX
    Explanations

    bioleaching, filtration, bacteria, oxidization

    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
    交æµģåIJĪä½ľ
    -0.07
    ulah
    -0.06
     eval
    -0.06
    çŃı
    -0.06
    orest
    -0.06
    åºĵéĩĮ
    -0.06
    ymar
    -0.06
     moz
    -0.06
     pandem
    -0.06
     Cellular
    -0.06
    POSITIVE LOGITS
     asc
    0.08
    建ç«ĭèµ·
    0.08
     изве
    0.08
    建ç«ĭ
    0.07
     ascend
    0.07
    ç¿Ķ
    0.07
    legt
    0.07
    áĪµ
    0.07
    SERVICE
    0.07
    ÏĦε
    0.07
    Activations Density 0.002%

    No Known Activations