© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20450
    Prev
    Next
    INDEX
    Explanations

    programming loops and variables

    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
    klan
    -0.06
    ille
    -0.06
    å¼ĢåĪ°
    -0.06
    elly
    -0.06
    è¿Ļä¹Īå¤ļ人
    -0.06
    客è¿IJç«Ļ
    -0.06
    ../../../
    -0.06
    ãĤ¨ãĥĶ
    -0.06
     Edinburgh
    -0.06
    createQuery
    -0.06
    POSITIVE LOGITS
    aida
    0.06
    éĺ»
    0.06
    rello
    0.06
    æį
    0.05
    åŃĺåľ¨
    0.05
    端
    0.05
    æijĬ
    0.05
    沿
    0.05
     init
    0.05
    å¹ħ
    0.05
    Activations Density 0.007%

    No Known Activations