© 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. 18646
    Prev
    Next
    INDEX
    Explanations

    birth years following names

    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
    anz
    -0.06
     pere
    -0.05
    èĢ³çĽ®
    -0.05
    绣ä¸Ģ
    -0.05
     пеÑĩ
    -0.05
     “
    -0.05
    tes
    -0.05
    æĽ¿
    -0.04
    à§įত
    -0.04
    anda
    -0.04
    POSITIVE LOGITS
    armo
    0.07
     !**
    0.07
     verle
    0.06
    akaan
    0.06
    à¹Ģà¸ķร
    0.06
    ukat
    0.06
    ÐļÑĢа
    0.06
    edList
    0.06
    ذاÙĨ
    0.06
    ç½ĹéĤ£
    0.06
    Activations Density 0.046%

    No Known Activations