© 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. 12137
    Prev
    Next
    INDEX
    Explanations

    copyright notice or study material

    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
    weight
    -0.07
    chel
    -0.07
     /\
    -0.07
    eze
    -0.07
    ENTITY
    -0.07
    indsay
    -0.07
    anda
    -0.06
    arkin
    -0.06
    人å¿ĥ弦
    -0.06
    ency
    -0.06
    POSITIVE LOGITS
    วà¸Ļ
    0.08
    âĺĨâĺĨ
    0.08
    Ģ
    0.07
    ainte
    0.07
    å§ĭèĩ³
    0.07
    ä½łåı¯
    0.06
    çºł
    0.06
    ç´ł
    0.06
    .net
    0.06
    ogs
    0.06
    Activations Density 0.001%

    No Known Activations