© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19615
    Prev
    Next
    INDEX
    Explanations

    nurse celldonor twin

    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
     combusti
    -0.09
     lana
    -0.07
     protes
    -0.07
     entende
    -0.07
     fras
    -0.07
    indagine
    -0.07
     diagnosti
    -0.07
    å¿«æĿ¥ä¸ĭè½½
    -0.07
     ÙģرÙĨ
    -0.07
     PureComponent
    -0.07
    POSITIVE LOGITS
     (
    0.07
    /
    0.07
    0.06
     as
    0.06
     S
    0.06
     "
    0.06
    S
    0.06
    <|endoftext|>
    0.05
     for
    0.05
    U
    0.05
    Activations Density 0.063%

    No Known Activations