© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19617
    Prev
    Next
    INDEX
    Explanations

    widely

    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
    åĿı
    -0.05
    æĤŁ
    -0.05
    odata
    -0.05
    hta
    -0.05
    enment
    -0.05
    æĪĸ以
    -0.05
     Everywhere
    -0.05
    Ùĥرر
    -0.05
    andise
    -0.05
    osphere
    -0.05
    POSITIVE LOGITS
    bola
    0.06
    é¡
    0.06
    ajs
    0.06
     lanc
    0.05
     hadn
    0.05
    placements
    0.05
    æĺĮå¹³
    0.05
    .he
    0.05
    bloc
    0.05
    äºĭæķħåıijçĶŁ
    0.05
    Activations Density 0.009%

    No Known Activations