© 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. 26872
    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
    大åı£
    -0.06
    ials
    -0.06
    i
    -0.06
    è¯Ŀ说
    -0.06
     nomin
    -0.06
     normal
    -0.05
    ä¸ĢåĪ»
    -0.05
    以åıĬå¦Ĥä½ķ
    -0.05
    Enum
    -0.05
     ":
    -0.05
    POSITIVE LOGITS
    astiche
    0.08
    enje
    0.08
    udging
    0.08
    idr
    0.08
    dpi
    0.08
    гой
    0.07
    anium
    0.07
    warts
    0.07
    utilus
    0.07
    çĮĽ
    0.07
    Activations Density 0.000%

    No Known Activations