© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    "Hello, World!"

    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
    adis
    -0.06
    ждÑĥÑİ
    -0.06
    ез
    -0.06
    ulasi
    -0.06
    ornos
    -0.06
    vars
    -0.06
     سخ
    -0.06
    _each
    -0.06
    åĶ¾
    -0.06
    ìĿ´ëĿ¼ëıĦ
    -0.06
    POSITIVE LOGITS
    opal
    0.06
    edException
    0.05
    lež
    0.05
    orem
    0.05
    ory
    0.05
     Paar
    0.05
    ÙĪبر
    0.05
    threat
    0.05
    omod
    0.05
    olor
    0.04
    Activations Density 0.002%

    No Known Activations