© 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. 21176
    Prev
    Next
    INDEX
    Explanations

    install

    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
     rush
    -0.06
    "bytes
    -0.05
    pring
    -0.05
    uts
    -0.05
    人们对äºİ
    -0.05
    ÙĪÙĩا
    -0.05
    elm
    -0.05
    urf
    -0.05
     bar
    -0.05
    ound
    -0.05
    POSITIVE LOGITS
    à¸ģà¸ķิ
    0.07
    ospel
    0.07
    Angeb
    0.06
    atel
    0.06
    жание
    0.06
    seb
    0.06
    unya
    0.06
    xima
    0.06
    ieb
    0.06
    Ķ
    0.06
    Activations Density 0.002%

    No Known Activations