© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39540
    Prev
    Next
    INDEX
    Explanations

    speed and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¼±
    -0.33
    çģµæķı
    -0.30
    æĸ°äº§åĵģ
    -0.27
    isode
    -0.26
     sensitivity
    -0.25
     relations
    -0.25
    èĥ½åĬĽå¼º
    -0.24
    éĵ¾æİ¥
    -0.24
    åįıè°ĥ
    -0.24
    çļĦè§Ĵ度
    -0.24
    POSITIVE LOGITS
    æµģ浪
    0.27
     Wid
    0.26
     opposed
    0.26
    ercul
    0.25
    arking
    0.25
    authenticate
    0.24
     Mixed
    0.24
     contested
    0.24
    EU
    0.23
    Mixed
    0.23
    Activations Density 1.611%

    No Known Activations