© 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. 22123
    Prev
    Next
    INDEX
    Explanations

    haiku poetry

    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
    ä¸Ģ个个
    -0.05
    anne
    -0.05
    iform
    -0.05
     demi
    -0.05
     impre
    -0.05
    æķ£
    -0.05
     li
    -0.05
    å°ıèĢĮ
    -0.05
    ken
    -0.05
     vi
    -0.05
    POSITIVE LOGITS
    åľ¨ä¸ĸ
    0.07
     ÑĥлиÑĨÑĥ
    0.06
    omy
    0.06
    зок
    0.06
    zuh
    0.06
    缸åħ³éĹ®çŃĶ
    0.06
    车系
    0.06
    奥æŀĹ
    0.06
     Gegen
    0.06
    å¦Ĥæ°´
    0.06
    Activations Density 0.001%

    No Known Activations