© 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. 20587
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

    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
    unge
    -0.06
    adm
    -0.05
    elian
    -0.05
    ׳×ĺ
    -0.05
    ocr
    -0.05
    instr
    -0.05
    é§
    -0.05
     اÙĦتش
    -0.05
    èİ«åIJįåħ¶
    -0.05
    нÑĨе
    -0.05
    POSITIVE LOGITS
    anisme
    0.06
     diras
    0.05
    Ñĭв
    0.05
     иÑģклÑİÑĩением
    0.05
    ropic
    0.05
    Äįit
    0.05
    δικ
    0.05
    åį³ä½¿
    0.05
    大éĢļ
    0.05
    رص
    0.05
    Activations Density 0.001%

    No Known Activations