© 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. 50859
    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
    ä¸įèĥľ
    -0.09
    imba
    -0.09
    agar
    -0.08
    essi
    -0.08
    usic
    -0.08
    cip
    -0.08
    ä¸ĩå²ģ
    -0.07
    åŃ£
    -0.07
    åĬŀ好
    -0.07
    νοÏį
    -0.07
    POSITIVE LOGITS
    tam
    0.07
    Ø©
    0.07
    anio
    0.06
    itava
    0.06
    iglio
    0.06
    人éģĵ
    0.06
     revelation
    0.06
    enzio
    0.06
    able
    0.06
    it
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.