© 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. 15405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Fld
    -0.07
    aina
    -0.06
    èĩªå·±çļĦ人
    -0.06
    é¨
    -0.06
    大æĪĺ
    -0.06
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.06
    å°ıé»Ħ
    -0.06
    çĭŀ
    -0.06
    gad
    -0.05
    æĽ´å¤ļçļĦ人
    -0.05
    POSITIVE LOGITS
    å¦ĤçĥŁ
    0.09
    zeuge
    0.08
     мÑĭÑģлÑĮ
    0.08
    _generic
    0.07
    òm
    0.07
    áĥ«
    0.07
    ôle
    0.07
    çĽ¸çŁ¥
    0.07
    ẵ
    0.07
    .da
    0.07
    Activations Density 0.000%

    No Known Activations