© 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. 61201
    Prev
    Next
    INDEX
    Explanations

    maintained level

    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
    .singleton
    -0.08
    认åĩĨ
    -0.08
    amaan
    -0.08
    æģ
    -0.07
    å³¥
    -0.07
    OPEN
    -0.07
    ÛĮÙĩ
    -0.07
    ruk
    -0.07
    æĿ¾æĩĪ
    -0.07
    ãĥĹãĥģ
    -0.07
    POSITIVE LOGITS
     compens
    0.10
    è¿Ļå°±è¦ģæ±Ĥ
    0.09
     artificially
    0.09
     gracias
    0.08
    éĩĩåıĸæݪæĸ½
    0.08
     компен
    0.08
     compensated
    0.08
     grâce
    0.07
    éĢļè¿ĩ使çĶ¨
    0.07
    éĢļè¿ĩå°Ĩ
    0.07
    Activations Density 0.031%

    No Known Activations