© 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. 38241
    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
    eldes
    -0.07
    ochrome
    -0.07
    oker
    -0.07
    æī§è¡ĮæĥħåĨµ
    -0.07
    è§ģæѤ
    -0.07
    esh
    -0.07
    abela
    -0.07
    appro
    -0.07
    åĶij
    -0.07
    áĥIJáĥ®
    -0.06
    POSITIVE LOGITS
    åĪĨ离
    0.08
    åĪĨéļĶ
    0.08
     separating
    0.08
    åĪĨéĽ¢
    0.07
     separates
    0.07
    orious
    0.07
    æĹłæķ°çļĦ
    0.07
     separated
    0.07
     separators
    0.07
    inga
    0.07
    Activations Density 0.000%

    No Known Activations