© 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. 45989
    Prev
    Next
    INDEX
    Explanations

    "Adam" followed by "son"

    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
    ¯
    -0.09
     Hoe
    -0.07
    é³
    -0.07
    ancı
    -0.07
    ogle
    -0.06
    æĹłèĥ½
    -0.06
    æĻĵ
    -0.06
    Unhandled
    -0.06
    ãģ¾ãģł
    -0.06
    _handles
    -0.06
    POSITIVE LOGITS
    å°¼å°Ķ
    0.08
    ystal
    0.08
    imageName
    0.07
    ilere
    0.07
    ãĥ¼ãĥī
    0.07
    å¹´æĺ¥åŃ£
    0.07
    èĥŀèĥİ
    0.07
    æĺ¯åįģåĪĨ
    0.07
    è®¤çľŁéĺħ读
    0.07
    ilding
    0.07
    Activations Density 0.379%

    No Known Activations