© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20947
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric sequences followed by punctuation or specific English 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
    -State
    -0.05
    Edward
    -0.05
     Hij
    -0.05
    åŁİ乡建设
    -0.05
    dep
    -0.05
     payloads
    -0.05
    è¿ŀç»Ń
    -0.05
    stur
    -0.05
    é¢Ĩå¥ĸ
    -0.05
    å°½æĥħ
    -0.05
    POSITIVE LOGITS
    รว
    0.06
    ä¸Ńè¡Į
    0.06
    IFT
    0.06
    udet
    0.06
    ajuan
    0.06
    erner
    0.06
    ons
    0.06
    jÃł
    0.06
    idth
    0.05
    åħ¶ä¸Ńæľī
    0.05
    Activations Density 0.086%

    No Known Activations