© 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. 24721
    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
    paginator
    -0.07
    ilde
    -0.07
     Dump
    -0.07
    ujung
    -0.07
    éch
    -0.07
    å¹´åį¡
    -0.06
    ackle
    -0.06
    chantment
    -0.06
     dump
    -0.06
    Dump
    -0.06
    POSITIVE LOGITS
    acific
    0.08
    çĶ±é«ĺ
    0.07
    解æĶ¾
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    èĦ¸
    0.07
    ä¸įå¿ĺ
    0.07
    veis
    0.07
    षà¥į
    0.07
    vé
    0.07
    arrant
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.