© 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. 22483
    Prev
    Next
    INDEX
    Explanations

    parsing and decoding data

    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
    order
    -0.06
    gan
    -0.06
    igan
    -0.06
    ed
    -0.05
    pos
    -0.05
    ä¸Ģ个大
    -0.05
    ainter
    -0.05
    os
    -0.05
    ãģĹãĤį
    -0.05
    osse
    -0.05
    POSITIVE LOGITS
    ëĭ¨
    0.06
    æģ¯
    0.06
    ubic
    0.06
    磨ç»ĥ
    0.05
    laus
    0.05
    pare
    0.05
    è£ħ饰设计
    0.05
    éĶ¤çĤ¼
    0.05
    azers
    0.05
     exponent
    0.05
    Activations Density 0.006%

    No Known Activations