© 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. 21476
    Prev
    Next
    INDEX
    Explanations

    lawyer or attorney specializing in legal matters

    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
    czyn
    -0.06
    线ä¸Ĭ
    -0.05
    ä¸ŃçĶŁ
    -0.05
    溶
    -0.05
    akin
    -0.05
    ä¸ĢæŃ¥æŃ¥
    -0.05
    s
    -0.05
    ä»ģ
    -0.05
    éĢĶ
    -0.05
    次
    -0.05
    POSITIVE LOGITS
     Transit
    0.06
     اÙĦÙĪÙĤ
    0.06
    顺åı£
    0.06
     IncluÃŃ
    0.06
     ervoor
    0.06
    avion
    0.06
    adet
    0.06
    iative
    0.06
    usern
    0.06
    غÙĬÙĦ
    0.06
    Activations Density 0.005%

    No Known Activations