© 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. 17114
    Prev
    Next
    INDEX
    Explanations

    currency symbols followed by 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
    acca
    -0.06
    iglio
    -0.06
    edos
    -0.06
    vez
    -0.06
    adurch
    -0.06
    kau
    -0.06
    ç´łæľī
    -0.06
    æĢķ
    -0.06
    uzz
    -0.06
     [][]
    -0.06
    POSITIVE LOGITS
    åѦåĪ°çļĦ
    0.05
    ster
    0.05
     tong
    0.05
     lab
    0.05
    ledge
    0.05
    izing
    0.05
    vc
    0.05
     Vitt
    0.05
    鼶åĶ®
    0.05
     m
    0.05
    Activations Density 0.010%

    No Known Activations