© 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. 64599
    Prev
    Next
    INDEX
    Explanations

    counterpart, complex, disorders, consideration, biography, process

    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
    åı¯è¨Ģ
    -0.08
    .openg
    -0.07
    ĻĤ
    -0.07
     mantu
    -0.07
     }]
    -0.07
    _failed
    -0.07
    åĿĤ
    -0.07
    abas
    -0.07
    Occurred
    -0.07
    åªĽåªĽ
    -0.07
    POSITIVE LOGITS
     étant
    0.12
     being
    0.10
    èĩªçĦ¶æĺ¯
    0.09
     коÑĤоÑĢого
    0.09
     is
    0.08
     bowiem
    0.08
    èĢħæĺ¯
    0.08
    à¸Ļีà¹īมี
    0.08
    æľ¬èº«å°±æĺ¯
    0.08
    ("").
    0.07
    Activations Density 0.470%

    No Known Activations