© 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. 21620
    Prev
    Next
    INDEX
    Explanations

    code array/list delimiters

    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
    ок
    -0.05
    bur
    -0.05
    uvian
    -0.05
    anks
    -0.05
    sv
    -0.05
    plies
    -0.05
    usi
    -0.05
    æīĢåľ¨
    -0.05
    ÃĹ
    -0.05
    æ´»åĬ¨
    -0.05
    POSITIVE LOGITS
    oref
    0.08
    å¾ģéĽĨ
    0.06
    Ùħع
    0.06
    証
    0.06
    èģ²æĺİ
    0.06
    à¸į
    0.06
    åd
    0.06
    èĬĿ
    0.06
    .createComponent
    0.06
    drop
    0.05
    Activations Density 0.024%

    No Known Activations