© 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. 18010
    Prev
    Next
    INDEX
    Explanations

    so followed by a word

    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
    forth
    -0.08
    åĽłæѤ
    -0.07
     Therefore
    -0.07
    bjerg
    -0.07
    èµĸ
    -0.06
     Hence
    -0.06
    quÃŃ
    -0.06
    Therefore
    -0.06
     anf
    -0.06
    oola
    -0.06
    POSITIVE LOGITS
    iksa
    0.05
    oz
    0.05
    å¤ĦçIJĨ设å¤ĩ
    0.05
    ãģ¨ãģ¯ãģĦãģĪ
    0.05
    ä½ķçŃī
    0.05
    ÙĪرش
    0.05
     dini
    0.05
    ÙĨØŃÙĨ
    0.05
    ij
    0.05
    Growing
    0.05
    Activations Density 0.025%

    No Known Activations