© 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. 34331
    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
    æĹłçĥŁ
    -0.07
    attes
    -0.07
    åĺŁåĺŁ
    -0.06
    ÙĪراÙĨ
    -0.06
    å¤§éĽ¨
    -0.06
     Kej
    -0.06
    éĽĨ
    -0.06
    _DAMAGE
    -0.06
    大å®ī
    -0.06
    uken
    -0.06
    POSITIVE LOGITS
    ç¼ħ
    0.07
    HT
    0.07
     наÑı
    0.07
    åİķ
    0.06
    /archive
    0.06
    ãĥ³ãĥĹ
    0.06
    itos
    0.06
    วà¸Ļ
    0.06
    ØŃÙĦ
    0.06
    ley
    0.06
    Activations Density 0.000%

    No Known Activations