© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20534
    Prev
    Next
    INDEX
    Explanations

    addition,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yles
    -0.06
    issement
    -0.06
    andez
    -0.06
     réflex
    -0.06
    ewan
    -0.06
    åı¦ä¸Ģè¾¹
    -0.06
    seys
    -0.06
    íķ¨ìĿĦ
    -0.06
    ruise
    -0.06
     rued
    -0.06
    POSITIVE LOGITS
    o
    0.06
    -
    0.05
    ilst
    0.05
    os
    0.05
    é¾Ħ
    0.05
    n
    0.05
    ¦
    0.05
    çļĦçĹĽèĭ¦
    0.05
    羣æŃ£çļĦ
    0.05
    оÑģ
    0.05
    Activations Density 0.012%

    No Known Activations