© 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. 18889
    Prev
    Next
    INDEX
    Explanations

    cheers or to followed by punctuation/articles

    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
    éĢĤçĶ¨çļĦ
    -0.07
    @s
    -0.07
     استÙģ
    -0.06
     kiá»ģm
    -0.06
    ackers
    -0.06
    enko
    -0.06
    à¸Ńà¸ļà¸Ńุà¹Īà¸Ļ
    -0.06
    ÑģÑĤила
    -0.06
     indeb
    -0.06
    åıĬ使çĶ¨
    -0.06
    POSITIVE LOGITS
     pivot
    0.06
    åħ´
    0.05
    çľī
    0.05
    ائÙĦ
    0.05
     redo
    0.05
    ifier
    0.05
    obo
    0.05
     инÑĤеÑĢеÑģ
    0.05
     piracy
    0.04
    ram
    0.04
    Activations Density 0.002%

    No Known Activations