© 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. 28206
    Prev
    Next
    INDEX
    Explanations

    simplicity discussed, assume

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    è¦ģæĮīçħ§
    -0.08
    íĨµ
    -0.07
     sobres
    -0.07
    éĿłå±±
    -0.07
    ÙĦات
    -0.07
    çļĦåIJĹ
    -0.07
    çŁ¥ãĤī
    -0.07
    åıĪåĥı
    -0.07
    avigate
    -0.07
    .lin
    -0.07
    POSITIVE LOGITS
    åĪĩ
    0.08
    以便
    0.08
    以便äºİ
    0.07
    åī
    0.07
     assume
    0.07
    以åħį
    0.07
    便äºİ
    0.07
     assum
    0.07
     representative
    0.07
     mewakili
    0.07
    Activations Density 0.041%

    No Known Activations