© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21195
    Prev
    Next
    INDEX
    Explanations

    exists

    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
    éľĢè¦ģèĢĥèĻij
    -0.06
    днÑı
    -0.05
     result
    -0.05
    ä¸įåIJ¬
    -0.05
    为ä»Ģä¹Īä¸į
    -0.05
    urs
    -0.05
     areas
    -0.05
    æĹłäºĭ
    -0.05
    ÑĥÑĢг
    -0.05
    urrency
    -0.05
    POSITIVE LOGITS
    illum
    0.06
    çĩ
    0.06
    ì¹Ń
    0.06
    init
    0.06
    initi
    0.06
    å¼ĤçķĮ
    0.06
    ä¾ł
    0.06
     affinché
    0.05
     väg
    0.05
    izen
    0.05
    Activations Density 0.073%

    No Known Activations