© 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. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23712
    Prev
    Next
    INDEX
    Explanations

    medical terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļ®èĤ¤
    -0.33
    èĤ¤
    -0.28
    _patches
    -0.27
    çļ®èĤ¤çĹħ
    -0.27
     tatto
    -0.27
    çĻ½çĻľé£İ
    -0.26
    SYS
    -0.26
     labor
    -0.25
    è¿Ļå¼ł
    -0.25
     Banner
    -0.24
    POSITIVE LOGITS
    éŨåīį
    0.27
    liner
    0.27
     Sentence
    0.27
    .export
    0.25
    IsEmpty
    0.25
    banks
    0.25
    å±İ
    0.24
    åĻİ
    0.24
     nuts
    0.24
    伶
    0.24
    Activations Density 0.003%

    No Known Activations