© 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. 10181
    Prev
    Next
    INDEX
    Explanations

    competitive, affine, Gaussian, passive, homogeneous, exchanged, face, attractive

    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
    çĶŁæ´»ä¸Ĭ
    -0.09
    istani
    -0.08
    heden
    -0.08
     ausgew
    -0.08
    orat
    -0.08
    entena
    -0.08
    Mahon
    -0.08
    ä¸Ńæŀ¢
    -0.07
    å°į象
    -0.07
    urma
    -0.07
    POSITIVE LOGITS
    åŀĭ
    0.08
    ment
    0.06
    å¼ı
    0.06
     nothing
    0.06
    veli
    0.06
    lide
    0.06
    بد
    0.06
     approach
    0.06
    许åı¯
    0.06
    ë¶Ħ
    0.06
    Activations Density 0.126%

    No Known Activations