© 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. 17888
    Prev
    Next
    INDEX
    Explanations

    digits and 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
    ail
    -0.05
    ably
    -0.05
     autant
    -0.05
    adders
    -0.05
    ch
    -0.05
    antage
    -0.05
    пÑĥлÑĮ
    -0.05
    èĽ
    -0.04
    SA
    -0.04
    fall
    -0.04
    POSITIVE LOGITS
    lesa
    0.07
    zett
    0.06
    wane
    0.06
    åħ¨æł¡å¸ĪçĶŁ
    0.06
    ône
    0.06
    ÙĦÙħات
    0.06
    ظÙĩ
    0.06
    idan
    0.06
    eby
    0.06
    ÙģÙĬر
    0.06
    Activations Density 0.037%

    No Known Activations