© 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. 18451
    Prev
    Next
    INDEX
    Explanations

    explaining complicated questions

    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
    atab
    -0.06
     criter
    -0.06
    ports
    -0.05
    åıįä¹ĭ
    -0.05
    ฤ
    -0.05
    isi
    -0.05
    æĦıçļĦ
    -0.05
    çĶ±é«ĺ
    -0.05
    акÑĤеÑĢ
    -0.05
    chie
    -0.05
    POSITIVE LOGITS
    ease
    0.06
    å¤ĦçIJĨ
    0.05
    handled
    0.05
     resolve
    0.05
     Fen
    0.05
    èĽ®
    0.05
    lef
    0.05
    çķĻç»Ļ
    0.05
    é¢IJ
    0.05
     unresolved
    0.05
    Activations Density 0.007%

    No Known Activations