© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    a methodology will

    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¸İä¼Ĺ
    -0.07
    chiere
    -0.06
    orial
    -0.06
    æªĢ
    -0.06
    mates
    -0.06
    endszer
    -0.06
    orme
    -0.06
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    aldo
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    POSITIVE LOGITS
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    oen
    0.05
    è¿ĺåĸľæ¬¢
    0.05
     outlined
    0.05
    Ìģ
    0.05
    ç°
    0.05
     acclaimed
    0.05
     risks
    0.05
    дина
    0.05
    临åħ¶
    0.05
    Activations Density 0.007%

    No Known Activations