© 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. 64563
    Prev
    Next
    INDEX
    Explanations

    "are not" / "are about" / "dear author"

    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
    åIJijä¸Ĭ级
    -0.09
    umi
    -0.08
    çĭĪ
    -0.08
    顾åIJįæĢĿ
    -0.08
    诽
    -0.08
    añ
    -0.08
    ãĥªãĥ¼ãĥĸ
    -0.08
    ä¹Ŀéĩį
    -0.08
    æĿ·
    -0.08
    æľĪçĶŁ
    -0.08
    POSITIVE LOGITS
    âĢ¦âĢ¦
    0.08
     âĢ¦
    0.06
     best
    0.06
    âĢ¦
    0.06
    пÑĭ
    0.06
     model
    0.06
    1
    0.06
    模èĮĥ
    0.05
    å¿ł
    0.05
    å¸ĮæľĽæĤ¨
    0.05
    Activations Density 0.005%

    No Known Activations