© 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. 22014
    Prev
    Next
    INDEX
    Explanations

    specific details or quantities

    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
     referenced
    -0.06
     siz
    -0.06
    azza
    -0.06
     varied
    -0.05
    ä¸ĢèĬĤ
    -0.05
     assorted
    -0.05
     nạn
    -0.05
     modifying
    -0.05
    æĪijä»¬çĽ¸ä¿¡
    -0.05
    -kit
    -0.05
    POSITIVE LOGITS
    emani
    0.06
    ôm
    0.06
    _cleanup
    0.06
    åħ¨éĥ¨è´£ä»»
    0.05
    лег
    0.05
    prene
    0.05
    öm
    0.05
    engt
    0.05
    yata
    0.05
    åħ¨æł¡å¸ĪçĶŁ
    0.05
    Activations Density 0.016%

    No Known Activations