© 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. 19986
    Prev
    Next
    INDEX
    Explanations

    given the

    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
    alent
    -0.05
    ç¦
    -0.05
    ucing
    -0.05
    ÙĬات
    -0.05
    æĺİ缮
    -0.05
    uden
    -0.05
    anks
    -0.05
    驾车
    -0.05
    um
    -0.05
    "
    -0.05
    POSITIVE LOGITS
    ØŃاÙħ
    0.06
    воÑĢо
    0.06
    alti
    0.06
    éİĸ
    0.06
    brem
    0.06
     garantis
    0.06
    æŶåĪ»
    0.06
    amma
    0.06
    /of
    0.06
    uyo
    0.06
    Activations Density 0.003%

    No Known Activations