© 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. 14722
    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
    ary
    -0.08
    åįĥç§ĭ
    -0.07
    çĹĩæĤ£èĢħ
    -0.07
    éłħ
    -0.07
    æİ´
    -0.07
    erat
    -0.07
    çĹĩ
    -0.07
    çĭĤ
    -0.07
    ural
    -0.07
     )"
    -0.07
    POSITIVE LOGITS
    ippe
    0.08
    ë°ĸìĹIJ
    0.07
    .lu
    0.06
    oley
    0.06
    ä¾¦çł´
    0.06
    å¼ºåĽ½
    0.06
    èĦijçŃĭ
    0.06
    åĨįä¹Łæ²¡æľī
    0.06
    centage
    0.06
     denk
    0.06
    Activations Density 0.000%

    No Known Activations