© 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. 18995
    Prev
    Next
    INDEX
    Explanations

    ademic

    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
    ed
    -0.08
    wykle
    -0.06
    ional
    -0.06
    ÑĢоÑģÑģий
    -0.06
    åѦéĩij
    -0.06
     Aragón
    -0.06
    iolet
    -0.06
    ons
    -0.06
    ing
    -0.06
    гоÑĤ
    -0.06
    POSITIVE LOGITS
    shaw
    0.07
    sey
    0.07
    à¹Ģà¸Īาะ
    0.06
    jing
    0.06
    меÑĩа
    0.06
    δÏĮ
    0.06
    iless
    0.06
     Nab
    0.06
     Bajo
    0.05
    odom
    0.05
    Activations Density 0.011%

    No Known Activations