© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30227
    Prev
    Next
    INDEX
    Explanations

    homozygous mutants, progeny, cousins

    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
    æĹłåıį
    -0.07
    å¥ĩçļĦ
    -0.07
    æĹłçĹķ
    -0.06
    åħ¨åı°
    -0.06
     Initialization
    -0.06
    _VARS
    -0.06
    ä¸İä¼Ĺä¸įåIJĮ
    -0.06
    maz
    -0.06
    人家çļĦ
    -0.06
    ith
    -0.06
    POSITIVE LOGITS
    ibes
    0.08
    å°ģæݧ
    0.07
     strat
    0.07
    yno
    0.07
    øk
    0.07
    gota
    0.07
    èĬ±èIJ½
    0.07
    tery
    0.07
    å¨ĵ
    0.07
    AINS
    0.07
    Activations Density 0.001%

    No Known Activations