© 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. 18735
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
    碰
    -0.06
     purposes
    -0.06
    zs
    -0.06
    ç»ı常
    -0.05
    åģļ
    -0.05
    à¹Ģà¸Ľà¹ĩà¸Ļà¸Ĺีà¹Ī
    -0.05
    åĴĮ
    -0.05
     FAM
    -0.05
    ä¸ºçĽ®çļĦ
    -0.05
    äºĨåIJĹ
    -0.05
    POSITIVE LOGITS
    edly
    0.07
    ibi
    0.07
    erable
    0.07
    ezo
    0.07
    ibo
    0.06
    该平åı°
    0.06
    çĿĢå°ı
    0.06
    ajaan
    0.06
    anei
    0.06
    ikkan
    0.06
    Activations Density 0.006%

    No Known Activations