© 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. 20029
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    ohn
    -0.06
    ollow
    -0.06
     tapis
    -0.06
    ä½İèĩ³
    -0.05
    oding
    -0.05
     therein
    -0.05
    åĵģ質
    -0.05
    дÑĢав
    -0.05
    å¯Ħ
    -0.05
    daw
    -0.05
    POSITIVE LOGITS
    aven
    0.05
    طة
    0.05
    æ¯Ķè¾ĥæľī
    0.05
    æĺ¯æĮĩåľ¨
    0.05
    atel
    0.05
     تسÙĦ
    0.05
    ubl
    0.05
    inned
    0.05
     intim
    0.05
    容
    0.05
    Activations Density 0.021%

    No Known Activations