© 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. 21102
    Prev
    Next
    INDEX
    Explanations

    command line interfaces

    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
    lesa
    -0.07
     espir
    -0.06
    exerc
    -0.06
    ابÙĤ
    -0.06
    compact
    -0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.06
     sle
    -0.06
     tov
    -0.06
    è¦ıç¯Ħ
    -0.06
    Ò³
    -0.06
    POSITIVE LOGITS
    é¦Ĩ
    0.05
    åįĬ
    0.05
    代
    0.05
     AMP
    0.05
    大æĺİ
    0.05
    éĨ¤æ²¹
    0.05
     ordering
    0.05
     construction
    0.05
    館
    0.05
    æ±Ĥ解
    0.04
    Activations Density 0.008%

    No Known Activations