© 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. 20091
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by nouns or verbs

    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
    è¨Ĺ
    -0.08
    dor
    -0.07
    ugu
    -0.07
    æŀķ
    -0.07
    ertain
    -0.06
    è¤ĩ
    -0.06
    é¼ĵèĪŀ
    -0.06
    upi
    -0.06
    iman
    -0.06
     Stations
    -0.06
    POSITIVE LOGITS
    æĶ¹è§Ĥ
    0.05
    æĸ½
    0.05
    æĶ¹éĢł
    0.05
    éªĦ
    0.05
    转åıĺ
    0.05
    gre
    0.05
     revised
    0.05
     nay
    0.05
    red
    0.05
    失
    0.05
    Activations Density 0.031%

    No Known Activations