© 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. 20510
    Prev
    Next
    INDEX
    Explanations

    preposition followed by a noun/pronoun

    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
    agy
    -0.07
    asonry
    -0.06
    adar
    -0.06
    ecca
    -0.06
    ecektir
    -0.06
    -automatic
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.06
    arna
    -0.06
    eced
    -0.06
    apol
    -0.06
    POSITIVE LOGITS
    æĸŃ
    0.06
    æĻĥ
    0.06
     opt
    0.06
    oust
    0.05
    å°½
    0.05
    æĮĩçļĦ
    0.05
     DeV
    0.05
     latter
    0.05
    ↵↵
    0.05
    k
    0.05
    Activations Density 0.001%

    No Known Activations