© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16551
    Prev
    Next
    INDEX
    Explanations

    ** musical keys (minor/major) **

    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
    Negative Logits
     Fanpage
    -0.07
    ู
    -0.06
    adir
    -0.06
    æ²³
    -0.06
    дневно
    -0.06
    åľ¨åģļ好
    -0.06
    lement
    -0.06
    .rawValue
    -0.06
    ганÑĤ
    -0.06
    figuration
    -0.06
    POSITIVE LOGITS
    åıĹçĽĬ
    0.06
    æŃ¤æ¬¡
    0.05
    éĹ´
    0.05
    çĹķ迹
    0.05
     pé
    0.05
     tra
    0.05
    åħį
    0.05
    patch
    0.05
    haul
    0.05
    ivid
    0.05
    Activations Density 0.003%

    No Known Activations