© 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. 12859
    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
    uct
    -0.07
    âĢ¦.
    -0.07
     Stéph
    -0.07
    ¹Ħ
    -0.07
    âĢ¦..
    -0.07
    umont
    -0.07
    ardi
    -0.07
    âĢ¦**
    -0.07
    ÑĥÑĤа
    -0.07
    åĪ©äºİ
    -0.07
    POSITIVE LOGITS
    æį¢åı¥è¯Ŀ说
    0.07
    )._
    0.07
    rompt
    0.07
    riors
    0.07
     atol
    0.06
    arshal
    0.06
    ront
    0.06
    ]._
    0.06
    jective
    0.06
    éĺħè¯»æľ¬æĸĩ
    0.06
    Activations Density 0.000%

    No Known Activations