© 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. 18131
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or alphanumeric codes

    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
    ulegen
    -0.07
    ç¨ĭ
    -0.06
    *'
    -0.06
    orma
    -0.06
    _bundle
    -0.06
    à¸Ńà¸ģà¸Īาà¸ģ
    -0.06
    cala
    -0.06
     btw
    -0.06
     tulev
    -0.06
    azion
    -0.06
    POSITIVE LOGITS
    s
    0.06
    ждÑĥÑİ
    0.06
    emis
    0.06
    _extra
    0.05
    ago
    0.05
    mith
    0.05
    è¡Įäºij
    0.05
    worth
    0.05
     lifes
    0.05
    ahan
    0.05
    Activations Density 0.046%

    No Known Activations