© 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. 13972
    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
    uld
    -0.09
    ifty
    -0.09
    benh
    -0.09
    ULD
    -0.09
    onar
    -0.08
    peed
    -0.08
    çĸ£
    -0.08
    leton
    -0.08
    zar
    -0.08
    åĽŀçŃĶéĩı
    -0.08
    POSITIVE LOGITS
    ru
    0.06
    åı«æĪij
    0.06
    çĪ±æĪij
    0.06
    mine
    0.06
    asan
    0.06
    çĪ±
    0.05
    ä¹Ŀä¹Ŀ
    0.05
    ä¸Ń继
    0.05
    æĬķ
    0.05
     I
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.