Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 146152
    Prev
    Next
    INDEX
    Explanations

    scientific/medical abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åīĤ
    -0.36
     drugs
    -0.35
    èį¯çī©
    -0.34
     chemicals
    -0.34
     chemical
    -0.33
    æľįç͍
    -0.32
    çļĦæķĪæŀľ
    -0.31
    èĹ¥
    -0.31
    èį¯åĵģ
    -0.31
    åĬij
    -0.31
    POSITIVE LOGITS
    orks
    0.30
    )section
    0.28
    æ±IJ
    0.27
     resil
    0.26
    æĭĨ
    0.26
    igmat
    0.25
     touched
    0.25
    atable
    0.24
    portun
    0.24
    Cri
    0.24
    Activations Density 0.038%

    No Known Activations