© 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. 19235
    Prev
    Next
    INDEX
    Explanations

    celebrate holidays and events

    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
    gli
    -0.07
    er
    -0.07
    æŶåĢĻ
    -0.07
    i
    -0.06
    ãģ¦ãĤĤ
    -0.06
    iop
    -0.06
    VAS
    -0.06
    ловÑĸ
    -0.06
    iems
    -0.06
    ieli
    -0.06
    POSITIVE LOGITS
    onom
    0.06
    æĶ»åĬ¿
    0.05
     const
    0.05
    ä¸į解
    0.05
    åĻ¨çļĦ
    0.05
     ë§Įìķ½
    0.05
    ÙĥÙĪÙĨ
    0.05
    åĪĨå·¥
    0.05
    OUND
    0.05
    åħ¶
    0.05
    Activations Density 0.009%

    No Known Activations