© 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. 21759
    Prev
    Next
    INDEX
    Explanations

    Based on the provided lists, here's the explanation for the neuron's behavior:numbers and units, money, or 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
    æĹ¶ä»£çļĦ
    -0.07
    gente
    -0.07
    à°Ĥà°Ł
    -0.07
    GOP
    -0.06
    ãĤıãĤĬãģ«
    -0.06
    çİīæłij
    -0.06
    æ²ĥæĸ¯
    -0.06
    iors
    -0.06
    åŃĹ第
    -0.06
    agri
    -0.06
    POSITIVE LOGITS
    z
    0.05
     zam
    0.05
     Driver
    0.05
    \\\\
    0.05
    oui
    0.04
     freedom
    0.04
     power
    0.04
     Mathematics
    0.04
    â
    0.04
    æݨ广
    0.04
    Activations Density 0.003%

    No Known Activations