© 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. 19305
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    åħ·
    -0.07
    ·¸
    -0.07
    acity
    -0.06
    lebihan
    -0.06
    furt
    -0.06
    plier
    -0.06
    untungan
    -0.06
    éĽ
    -0.06
    ä¸ĭè½½çĻ¾åº¦çŁ¥éģĵ
    -0.06
    rocessing
    -0.06
    POSITIVE LOGITS
    æĺĤ
    0.06
    기를
    0.05
    è¯Ŀ说
    0.05
     parse
    0.05
     ambigu
    0.05
     ancestors
    0.05
    :
    0.05
    ÑĢаÑĤ
    0.05
     entre
    0.05
    å¾Ĺè¿ĩ
    0.05
    Activations Density 0.001%

    No Known Activations