© 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. 33744
    Prev
    Next
    INDEX
    Explanations

    understanding and interpretation

    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
    orgia
    -0.08
    оÑĢа
    -0.07
    à¸Ńà¸Ļ
    -0.07
    kait
    -0.07
    anh
    -0.07
    æĶ¹åIJį
    -0.07
     УÑĩ
    -0.06
    ikum
    -0.06
    oute
    -0.06
    踪影
    -0.06
    POSITIVE LOGITS
    interpret
    0.11
    解读
    0.11
     Interpret
    0.10
     interpretation
    0.10
     meanings
    0.10
     meaning
    0.10
     interpretations
    0.09
    åIJ«ä¹ī
    0.09
     ÑĤÑĢак
    0.09
     interpret
    0.09
    Activations Density 0.029%

    No Known Activations