© 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. 18309
    Prev
    Next
    INDEX
    Explanations

    ending with specific characters or words

    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
    缴æİ¥æĬĬ
    -0.06
     artific
    -0.06
    npc
    -0.05
    缴æİ¥å°Ĩ
    -0.05
    onga
    -0.05
    ULT
    -0.05
     kepala
    -0.05
    acking
    -0.05
     Platt
    -0.05
     sever
    -0.05
    POSITIVE LOGITS
    orno
    0.06
     traces
    0.05
    à¸Ļัà¸Ķ
    0.05
    yz
    0.05
    æĬ½
    0.05
     جذ
    0.05
    åħ¬çĽĬæ´»åĬ¨
    0.05
    åĵĪå¸Į
    0.05
    å°ijèµ°
    0.05
     known
    0.05
    Activations Density 0.001%

    No Known Activations