© 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. 63524
    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
    itecture
    -0.08
    æĿ¥å¾ĹåıĬ
    -0.08
    imore
    -0.08
    <|box_end|>
    -0.08
    åĵĶåĵ©
    -0.08
    æľīéľĢè¦ģ
    -0.08
    缸åħ³æĥħåĨµ
    -0.08
    ä¸į移
    -0.08
    缸åħ³èµĦæĸĻ
    -0.07
    ä¸į失
    -0.07
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.07
    odin
    0.06
    è¤Ĥ
    0.06
    ãģłãģij
    0.06
    etas
    0.06
    enio
    0.06
    è¦ģä¹Ī
    0.06
    轩
    0.06
    apas
    0.06
     s
    0.06
    Activations Density 0.000%

    No Known Activations