© 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. 19979
    Prev
    Next
    INDEX
    Explanations

    U.S

    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
    fera
    -0.06
    åºĹéķĩ
    -0.06
    erschein
    -0.06
    assis
    -0.06
    eking
    -0.06
    äºĨä½łçļĦ
    -0.06
    atha
    -0.06
    ãĥķãĤ£ãĥ¼
    -0.06
    porto
    -0.06
    меÑĢ
    -0.06
    POSITIVE LOGITS
     ext
    0.06
    èģ
    0.05
    æłĩ示
    0.05
    bies
    0.05
     spo
    0.05
    uary
    0.05
    خاذ
    0.05
     eyebrows
    0.05
    igts
    0.05
    ally
    0.05
    Activations Density 0.002%

    No Known Activations