© 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. 33076
    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
     Edels
    -0.07
    ono
    -0.07
    akit
    -0.07
    aket
    -0.07
     distress
    -0.07
    jeg
    -0.07
    Æ°u
    -0.07
    apel
    -0.07
     rued
    -0.07
    åijķ
    -0.07
    POSITIVE LOGITS
    mpl
    0.06
    uada
    0.06
    åĭĩ士
    0.06
    ä¸īéģĵ
    0.06
    van
    0.06
     showModal
    0.06
    çĨĻ
    0.06
    hes
    0.05
    å¢ŀ
    0.05
    åĨħéĥ¨æݧåĪ¶
    0.05
    Activations Density 0.000%

    No Known Activations