© 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. 28660
    Prev
    Next
    INDEX
    Explanations

    URL encoding with params

    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
    iette
    -0.07
    olly
    -0.07
    igar
    -0.07
    ellig
    -0.07
    çļĦåŃĺåľ¨
    -0.06
    errar
    -0.06
     Mans
    -0.06
    å¦Īå¦Ī说
    -0.06
    ниÑĨ
    -0.06
    inn
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.08
    alu
    0.08
     برد
    0.08
    uret
    0.07
    ugning
    0.07
    çŃī缸åħ³
    0.07
    éļĪ
    0.07
    ä¾ĽåºĶ产åĵģ
    0.07
    注æĦıçļĦæĺ¯
    0.07
    ä¼ģä¸ļ对
    0.07
    Activations Density 0.008%

    No Known Activations