© 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. 22142
    Prev
    Next
    INDEX
    Explanations

    mathematical operations with 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
    å½¼
    -0.06
    ationally
    -0.06
    å°½
    -0.06
    å¦ĸåŃ½
    -0.05
    离
    -0.05
     eff
    -0.05
    des
    -0.05
    -ground
    -0.05
    elines
    -0.05
    çľ¨çľ¼
    -0.05
    POSITIVE LOGITS
    Ñijд
    0.06
    اÛģ
    0.06
    Ã¤ÃŁ
    0.05
    éģĵ家
    0.05
    quat
    0.05
    æ³°
    0.05
    aln
    0.05
     levado
    0.05
    rá
    0.05
    lage
    0.05
    Activations Density 0.020%

    No Known Activations