© 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. 15279
    Prev
    Next
    INDEX
    Explanations

    relational coordination, heuristic, -II, nested models, mimic, competition

    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
    prus
    -0.08
    plx
    -0.08
     abat
    -0.08
    满满
    -0.08
     terecht
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    é¼İé¼İ
    -0.07
    èĢģ头
    -0.07
    succ
    -0.07
    ä¹ĭ交
    -0.07
    POSITIVE LOGITS
    åIJįåī¯
    0.07
    PMC
    0.06
     progress
    0.06
    å°ıåŁİ
    0.06
    assembly
    0.06
     hô
    0.05
    å·²ç»ı被
    0.05
     flank
    0.05
    fø
    0.05
    idium
    0.05
    Activations Density 0.074%

    No Known Activations