© 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. 18502
    Prev
    Next
    INDEX
    Explanations

    **Analyzing Neuron Inputs**Here's the explanation for the neuron's behavior:lists of items

    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
     unab
    -0.06
    volume
    -0.06
    ühlen
    -0.06
     ÑħоÑĤÑĮ
    -0.06
    udit
    -0.05
    .Mutable
    -0.05
    æĪĸ个人
    -0.05
    vely
    -0.05
     ngá»įt
    -0.05
     intentionally
    -0.05
    POSITIVE LOGITS
    resse
    0.07
    è¯Ŀ
    0.07
    æ´²
    0.06
    zÄĻ
    0.06
    好å¤ĦçļĦ
    0.06
    azin
    0.06
    紧缩
    0.06
    iewicz
    0.05
    äºķ
    0.05
    æIJŃè½½äºĨ
    0.05
    Activations Density 0.003%

    No Known Activations