© 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. 21728
    Prev
    Next
    INDEX
    Explanations

    law firms or business services

    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
     conditions
    -0.05
     маÑĤ
    -0.05
    åī²
    -0.05
    bed
    -0.04
     voz
    -0.04
     stew
    -0.04
     ut
    -0.04
     ÑĤÑĬ
    -0.04
    涨
    -0.04
    SS
    -0.04
    POSITIVE LOGITS
    被客æĪ·
    0.08
    äºĭåĬ¡æīĢ
    0.07
    å¸ĪçļĦ
    0.07
    TEMPLATE
    0.07
    baz
    0.06
    对客æĪ·
    0.06
    siz
    0.06
    aime
    0.06
    abad
    0.06
    encil
    0.06
    Activations Density 0.159%

    No Known Activations