© 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. 24325
    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
    >,</
    -0.08
    ellig
    -0.08
    æĦıæĥ³ä¸įåĪ°
    -0.08
    eling
    -0.08
    æĥ¹äºº
    -0.07
    usher
    -0.07
    å¨ģæµ·
    -0.07
    ×ijר×Ķ
    -0.07
     Baj
    -0.07
     бÑĭ
    -0.07
    POSITIVE LOGITS
    aea
    0.07
    ispers
    0.06
    åıĬéĻĦåĬł
    0.06
    anol
    0.06
    ""
    0.06
     جÙħ
    0.05
    ilter
    0.05
    è®°åıĻ
    0.05
    æĹłæĤĶ
    0.05
    .time
    0.05
    Activations Density 0.000%

    No Known Activations