© 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. 20942
    Prev
    Next
    INDEX
    Explanations

    United States

    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
     pek
    -0.06
    %i
    -0.06
     enctype
    -0.06
    ãģĭãģij
    -0.06
    uele
    -0.06
    acu
    -0.06
    hower
    -0.06
    å®ĪèŃ·
    -0.06
    нÑĮ
    -0.06
    åı·çīĮ
    -0.05
    POSITIVE LOGITS
    以å¾ħ
    0.06
    ستÙħ
    0.05
    岸
    0.05
    achel
    0.05
    دÙĬات
    0.05
    ç¿
    0.05
    åIJ¹
    0.05
    æľī家
    0.05
    è©ķåĪ¤
    0.05
    æĹ¥åĴĮ
    0.05
    Activations Density 0.019%

    No Known Activations