© 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. 49383
    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
    å°¤åħ¶æĺ¯
    -0.07
    ä¸ĢåIJij
    -0.06
    说ä»Ģä¹Ī
    -0.06
    æ¯Ķå¦Ĥ
    -0.06
    è®
    -0.06
    çĸ¯äºĨ
    -0.06
    .
    -0.06
    erti
    -0.06
     especially
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
    POSITIVE LOGITS
    ÐŁÐ¡
    0.09
    éģĹçĹĩ
    0.08
    rech
    0.08
    angsa
    0.08
    eeper
    0.07
    ÐļС
    0.07
    æķµ
    0.07
    qid
    0.07
    ighed
    0.07
    åİŁçĶŁ
    0.07
    Activations Density 0.000%

    No Known Activations