© 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. 20395
    Prev
    Next
    INDEX
    Explanations

    other [noun]

    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
    /she
    -0.05
    achers
    -0.05
    quire
    -0.05
    arbe
    -0.05
    лиÑĩ
    -0.05
    amba
    -0.05
    лÑıÑĢ
    -0.05
    -0.05
    ardo
    -0.05
    ä¸Ģçݯ
    -0.05
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.08
    åħ¶å®ĥçļĦ
    0.08
     other
    0.07
    åĪ«çļĦ
    0.07
    важа
    0.07
    orable
    0.06
    åħ¶ä»ĸ
    0.06
     outros
    0.06
     outras
    0.06
    other
    0.06
    Activations Density 0.061%

    No Known Activations