© 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. 21996
    Prev
    Next
    INDEX
    Explanations

    signed numbers

    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
    agr
    -0.07
    宾
    -0.06
    andon
    -0.06
    éĻµ
    -0.06
    columns
    -0.05
     возÑĢа
    -0.05
    乡æĿij
    -0.05
    ä¸īä¸ĸ
    -0.05
     projections
    -0.05
    循çݯ
    -0.05
    POSITIVE LOGITS
    åĬĪ
    0.05
    çļ®
    0.05
    èİ«åIJįåħ¶å¦Ļ
    0.05
    ä¿®æķ´
    0.05
     lä
    0.05
     pac
    0.05
     écl
    0.05
    éĹª
    0.05
     legit
    0.05
     tracker
    0.05
    Activations Density 0.015%

    No Known Activations