© 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. 16802
    Prev
    Next
    INDEX
    Explanations

    capabilities and tasks

    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
    ä¸İ人
    -0.06
    elman
    -0.06
    abil
    -0.06
    ä¸İåѦçĶŁ
    -0.05
    åľ¨äºº
    -0.05
    lah
    -0.05
    å±Ĥ
    -0.05
    âĸ¡
    -0.05
    UMAN
    -0.05
    ä»Ģä¹Ī
    -0.05
    POSITIVE LOGITS
    ÑĤо
    0.06
    stens
    0.06
    ÑĤÑģÑı
    0.05
    é£İå°ĺ
    0.05
    astiche
    0.05
    olding
    0.05
    åľŁåľ°ä½¿çĶ¨
    0.05
    _ak
    0.05
    <ArrayList
    0.05
    ovich
    0.05
    Activations Density 0.210%

    No Known Activations