© 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. 17451
    Prev
    Next
    INDEX
    Explanations

    recursive client port source

    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
    afür
    -0.06
    achi
    -0.06
    عب
    -0.06
    adel
    -0.06
    jian
    -0.05
    acr
    -0.05
    /or
    -0.05
    ÛĮا
    -0.05
    sut
    -0.05
    è¦ı
    -0.05
    POSITIVE LOGITS
    Ìģ
    0.07
    eles
    0.06
    e
    0.06
    ersch
    0.06
    é¡¿äºĨ
    0.06
    طة
    0.05
    erschaft
    0.05
    æ°ĶäºĨ
    0.05
    emment
    0.05
    estion
    0.05
    Activations Density 0.013%

    No Known Activations