© 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. 18981
    Prev
    Next
    INDEX
    Explanations

    writing and technical terms

    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
    abo
    -0.06
    tes
    -0.06
     fis
    -0.05
    ças
    -0.05
    ASE
    -0.05
    ä¼ģä¸ļåĨħéĥ¨
    -0.05
    lab
    -0.05
     ì¢ħ
    -0.05
    sp
    -0.05
    .random
    -0.05
    POSITIVE LOGITS
    illeurs
    0.07
    raud
    0.06
    ikit
    0.06
    å«©çļĦ
    0.06
    ulating
    0.06
    ówczas
    0.06
    erder
    0.06
    alling
    0.06
    elen
    0.06
    ertime
    0.06
    Activations Density 0.131%

    No Known Activations