© 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. 20242
    Prev
    Next
    INDEX
    Explanations

    pronouns following by nouns

    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
    æīĢ欲
    -0.06
    è¿ĻäºĽæķ°æį®
    -0.05
    onet
    -0.05
    afil
    -0.05
    onen
    -0.05
    ffer
    -0.05
    è¿ĻäºĽåľ°æĸ¹
    -0.05
     Fras
    -0.05
    åįłåħ¬åı¸
    -0.05
    aff
    -0.05
    POSITIVE LOGITS
    enaar
    0.06
    stuhl
    0.06
    otle
    0.06
    енеÑĢа
    0.05
    åħ·ä½ĵ
    0.05
    天çİĭ
    0.05
    ices
    0.05
    羣çļĦ好
    0.05
    UAL
    0.05
    .true
    0.05
    Activations Density 0.039%

    No Known Activations