© 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. 65182
    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
    缸è¾ħ缸æĪIJ
    -0.07
    urn
    -0.07
    åĪ°ä»Ģä¹Ī
    -0.07
    owl
    -0.07
    çģ¶
    -0.07
    ç½Ħ
    -0.06
    бий
    -0.06
    leb
    -0.06
    Ñĥз
    -0.06
    ÙĦز
    -0.06
    POSITIVE LOGITS
    ydd
    0.08
     pragma
    0.07
    Äĥm
    0.07
    WithPath
    0.07
    Mounted
    0.07
    ÞĤ
    0.07
     alun
    0.07
    تاÙĨ
    0.07
    ëŀij
    0.07
    urette
    0.07
    Activations Density 0.000%

    No Known Activations