© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19918
    Prev
    Next
    INDEX
    Explanations

    introductions and conjunctions

    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
    uw
    -0.07
     thereof
    -0.07
    wc
    -0.06
    og
    -0.06
    mage
    -0.05
    tron
    -0.05
    arta
    -0.05
    书çŃ¾
    -0.05
    fun
    -0.05
    hw
    -0.05
    POSITIVE LOGITS
     irres
    0.05
    iraz
    0.05
    ä¸įå¤ĸ
    0.05
    effectuer
    0.05
    perfil
    0.05
     cláus
    0.05
    ä¸Ĭ马
    0.05
    ampak
    0.05
    emblée
    0.05
     سÙĬا
    0.05
    Activations Density 0.021%

    No Known Activations