© 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. 20680
    Prev
    Next
    INDEX
    Explanations

    it followed by punctuation or specific words

    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
    ä¼ļåıĺæĪIJ
    -0.06
     Fran
    -0.06
    -0.06
    मान
    -0.06
    ournemouth
    -0.06
    ä¼ļå¾Ī
    -0.06
    orna
    -0.06
     opr
    -0.06
    izedName
    -0.06
    unker
    -0.06
    POSITIVE LOGITS
    atos
    0.06
    äºĪ
    0.05
    лÑİ
    0.05
    ató
    0.05
    ck
    0.05
    etas
    0.05
    +/
    0.05
    ets
    0.05
    å¸ĥ
    0.05
    å¤ļæľĪ
    0.05
    Activations Density 0.002%

    No Known Activations