© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50017
    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
    UID
    -0.07
    vain
    -0.07
    æ£īèĬ±
    -0.06
    åĮħ
    -0.06
    ailles
    -0.06
    _UID
    -0.06
    èľĤ
    -0.06
    åĩºåĶ®
    -0.06
    èĥŀèĥİ
    -0.06
    ik
    -0.06
    POSITIVE LOGITS
    positor
    0.09
    åŃĺæľī
    0.09
    ehm
    0.08
    éĩijé¾Ļ
    0.08
     rejo
    0.08
    سط
    0.08
    碩
    0.08
    omatic
    0.07
    ¿
    0.07
    Epoch
    0.07
    Activations Density 0.000%

    No Known Activations