© 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. 20890
    Prev
    Next
    INDEX
    Explanations

    low things

    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
    yp
    -0.06
    олÑĮ
    -0.06
    æ´¼
    -0.05
    amol
    -0.05
    or
    -0.05
    ach
    -0.05
    æĪĸ缺
    -0.05
    éĢĢ
    -0.05
    çĥŃéŨæݨèįIJ
    -0.05
    ä¸Ķä¸į
    -0.05
    POSITIVE LOGITS
    etroit
    0.06
    bringung
    0.06
    ÑģÑĤÑĢоен
    0.06
    代è¡Į
    0.06
    brace
    0.06
    наÑĩе
    0.06
    ãģłãģĦ
    0.06
    lect
    0.06
     araya
    0.06
    大åħ´
    0.06
    Activations Density 0.001%

    No Known Activations