© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    electroactive compounds and transport layers

    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
    åĨħçļĦ
    -0.07
    ARED
    -0.07
    Ñģле
    -0.07
    æıIJä¾Ľæĸ¹
    -0.07
    bay
    -0.07
    .clients
    -0.07
    ãģķãģĦ
    -0.07
    imaan
    -0.06
    पाल
    -0.06
    mé
    -0.06
    POSITIVE LOGITS
    ensive
    0.08
    oren
    0.08
    icona
    0.07
    encial
    0.07
    æĸ¹å¼ı为
    0.07
    对æѤä¸įæī¿æĭħä»»ä½ķ
    0.07
    ermo
    0.07
    entic
    0.07
    eth
    0.07
     via
    0.07
    Activations Density 0.001%

    No Known Activations