© 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. 19661
    Prev
    Next
    INDEX
    Explanations

    biotechnology and related fields

    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
    adrž
    -0.06
    INES
    -0.06
    urv
    -0.06
    æݢ讨
    -0.06
    roup
    -0.06
    åİŁåľ°
    -0.05
    attern
    -0.05
    å¶
    -0.05
    biz
    -0.05
     Surv
    -0.05
    POSITIVE LOGITS
     molecular
    0.05
    inos
    0.05
    olecular
    0.05
    åŀ¦
    0.05
     mole
    0.05
     fertil
    0.05
    æīĵæĪIJ
    0.05
    пив
    0.05
    åįģåŃĹ
    0.05
     antis
    0.05
    Activations Density 0.033%

    No Known Activations