© 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. 17854
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to self or others

    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
     vitae
    -0.06
    ä½°
    -0.06
    æīijé¼»
    -0.06
     limp
    -0.06
    ctic
    -0.06
    èĩªçŁ¥
    -0.06
    èĩªåĬ¨æĶ¾å¼ĥ
    -0.05
    arre
    -0.05
    å±Ĩ
    -0.05
     immédi
    -0.05
    POSITIVE LOGITS
    ston
    0.06
     in
    0.05
     sp
    0.05
     separate
    0.05
    sp
    0.05
    人家
    0.05
    aced
    0.05
     ske
    0.05
    åĴĮåѦçĶŁ
    0.05
     se
    0.05
    Activations Density 0.011%

    No Known Activations