© 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. 24381
    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
     Olah
    -0.07
    undra
    -0.07
    åĨ»
    -0.07
    è¾ĵåħ¥çļĦ
    -0.07
    跨年
    -0.07
     frost
    -0.07
    criptor
    -0.07
     terminal
    -0.06
     Wick
    -0.06
     borderline
    -0.06
    POSITIVE LOGITS
    ä½ĵ积
    0.08
    æ¯Ķéĩį
    0.08
    æµ®
    0.08
    æµģä½ĵ
    0.07
     Fluid
    0.07
     Gaya
    0.07
    容积
    0.07
     fluids
    0.07
    (det
    0.07
    elper
    0.07
    Activations Density 0.000%

    No Known Activations