© 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. 17169
    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
    ÙĬار
    -0.07
     un
    -0.06
     increment
    -0.06
    ë£
    -0.06
    æĺİæĻº
    -0.05
    åĿĬ
    -0.05
     y
    -0.05
    bia
    -0.05
     increments
    -0.05
    åĪĢ
    -0.05
    POSITIVE LOGITS
    igin
    0.08
     Cty
    0.08
    digt
    0.08
     ÐŁÐ¾Ð¿ÑĢо
    0.08
     besti
    0.08
    ippines
    0.08
    LOTS
    0.08
    åħĪçĶŁè¯´
    0.08
    pcodes
    0.08
    amble
    0.08
    Activations Density 0.000%

    No Known Activations