© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19467
    Prev
    Next
    INDEX
    Explanations

    legal or illegal drugs

    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
     fou
    -0.05
    åħ±
    -0.05
     dev
    -0.05
    ìĤ¬íķŃ
    -0.05
    ä¸Ĭä¸Ģ次
    -0.05
    èģĮ
    -0.05
     pollution
    -0.04
    reiz
    -0.04
    åľ¨çİ°åľº
    -0.04
    è¶Ĭ
    -0.04
    POSITIVE LOGITS
    odus
    0.07
    kke
    0.07
     تÙĨا
    0.06
    ведений
    0.06
    ÙĬراد
    0.06
    BUFF
    0.06
    çĻ¾è®¡
    0.06
     Levante
    0.06
    óz
    0.06
    alité
    0.06
    Activations Density 0.021%

    No Known Activations