© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21595
    Prev
    Next
    INDEX
    Explanations

    summary

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éģIJ
    -0.05
    æĸ¹çļĦ
    -0.05
    代åħ¥
    -0.05
    æ¸ħäºĨ
    -0.05
    éļĶ
    -0.05
    ç«Ļåľ¨
    -0.05
     неза
    -0.05
    apor
    -0.05
    åĭĻ
    -0.05
     deeper
    -0.05
    POSITIVE LOGITS
    å®°
    0.07
    å®Īä¿¡
    0.06
    æľ¬æĸĩéĵ¾æİ¥
    0.06
    hez
    0.06
    etty
    0.06
    izz
    0.06
    heit
    0.06
     estadounid
    0.05
    ç´¢åıĸ
    0.05
    *@
    0.05
    Activations Density 0.012%

    No Known Activations