© 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. 22596
    Prev
    Next
    INDEX
    Explanations

    `a[`, `a[n]`

    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
    ÑĤе
    -0.07
     ménage
    -0.06
    ÙĨÙĬÙĨ
    -0.06
    çİ°
    -0.06
    æ¸ħç®Ĺ
    -0.06
    /npm
    -0.05
    åĴ½
    -0.05
    antt
    -0.05
    çİ°å·²
    -0.05
    fout
    -0.05
    POSITIVE LOGITS
    ument
    0.06
    inst
    0.06
    ur
    0.06
    add
    0.06
     motiv
    0.05
    涡轮å¢ŀåİĭåıijåĬ¨æľº
    0.05
     Systems
    0.05
    omat
    0.05
     aside
    0.05
     Addition
    0.05
    Activations Density 0.029%

    No Known Activations