© 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. 56658
    Prev
    Next
    INDEX
    Explanations

    separators and formatting

    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
    Ïīνα
    -0.07
    å¤ķ
    -0.07
     Dim
    -0.07
    mey
    -0.07
    å¾Ĺè¿ĩ
    -0.07
     Ridley
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    urger
    -0.07
    åħ¶äºĭ
    -0.07
    Dim
    -0.07
    POSITIVE LOGITS
    å¹¼
    0.08
    åĮł
    0.07
    ÑĢак
    0.07
     unc
    0.07
    odian
    0.07
    ilden
    0.07
     Poe
    0.07
     Burnett
    0.06
    幼年
    0.06
    .code
    0.06
    Activations Density 0.079%

    No Known Activations