© 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. 20750
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by prepositions or adverbs

    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
    akup
    -0.06
    antik
    -0.06
    浸
    -0.06
    -any
    -0.06
    ÙĪسÛĮ
    -0.06
    ÃŃas
    -0.06
     ekl
    -0.05
    obil
    -0.05
    éľĢè¦ģäºĨ解
    -0.05
    ear
    -0.05
    POSITIVE LOGITS
    å¹³
    0.06
    åįİ为
    0.05
    ä¸ļ
    0.05
    rending
    0.05
    ØŃÙĨ
    0.05
    åģı
    0.05
     ΣÏĦην
    0.05
    ç¯ĵ
    0.05
     appoint
    0.05
    ê°ģ
    0.05
    Activations Density 0.075%

    No Known Activations