© 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. 19700
    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
     voilÃł
    -0.08
    ostar
    -0.07
    .swagger
    -0.07
    ä¸įå°ı
    -0.07
    åı·ä»¤
    -0.07
    øv
    -0.07
    ëĭĪëĭ¤
    -0.07
    øre
    -0.07
    ä¸Ģå²ģ
    -0.07
    rift
    -0.07
    POSITIVE LOGITS
    mano
    0.09
    baugh
    0.07
    awei
    0.07
    erts
    0.07
    è´¢
    0.06
    ignano
    0.06
    çĶ±ä¹Ļæĸ¹
    0.06
    å¾Ĵ
    0.06
    -INF
    0.06
    adi
    0.06
    Activations Density 0.000%

    No Known Activations