© 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. 17487
    Prev
    Next
    INDEX
    Explanations

    law and regulations

    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
    ÑĤÑĢа
    -0.06
    rody
    -0.05
    AKE
    -0.05
    ारा
    -0.05
     صاد
    -0.05
    ãĤģãģ®
    -0.05
     sämt
    -0.05
    AINS
    -0.05
    stin
    -0.05
    ahan
    -0.05
    POSITIVE LOGITS
    orrag
    0.06
    dv
    0.06
    urrect
    0.05
    scenario
    0.05
     Rally
    0.05
     rig
    0.05
    uffy
    0.05
     sound
    0.05
    åı¯ä»¥æĮīçħ§
    0.05
    工夫
    0.05
    Activations Density 0.063%

    No Known Activations