© 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. 22036
    Prev
    Next
    INDEX
    Explanations

    " the " followed by specific words

    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
    æĸ°çĶŁçļĦ
    -0.06
    å¾Īå¿Ļ
    -0.06
    ders
    -0.06
    teras
    -0.05
    å¾Īå¼Ģå¿ĥ
    -0.05
    oder
    -0.05
     unsus
    -0.05
    hit
    -0.05
    eller
    -0.05
    çļĦéĢŁåº¦
    -0.05
    POSITIVE LOGITS
    naan
    0.06
    irian
    0.05
     well
    0.05
    imm
    0.05
    åı²ä¸Ĭ
    0.05
    ↵				↵
    0.05
    ieza
    0.05
     worth
    0.05
    éĵ²
    0.05
    alma
    0.05
    Activations Density 0.009%

    No Known Activations