© 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. 22143
    Prev
    Next
    INDEX
    Explanations

    ssl encryption

    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
    à¸ļาล
    -0.07
    kaan
    -0.06
    ambo
    -0.06
    亳
    -0.06
     Copp
    -0.05
    agram
    -0.05
    ocol
    -0.05
    guer
    -0.05
    ycz
    -0.05
    поÑĢ
    -0.05
    POSITIVE LOGITS
    iana
    0.07
    äºĨä¸ĢåĪĩ
    0.06
    åIJĦ级åIJĦç±»
    0.05
    ètes
    0.05
    .convert
    0.05
    ä¸Ģ串
    0.05
     ranges
    0.05
    енÑĭ
    0.05
    æľ«
    0.05
     everywhere
    0.05
    Activations Density 0.002%

    No Known Activations