© 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. 19-TRANSCODER-HP
    7. 9501
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     resulting
    -0.31
    sek
    -0.31
    apos
    -0.27
    ForResult
    -0.26
    wers
    -0.26
    å¤Ħç½ļ
    -0.25
    andscape
    -0.24
    ä»Ģä¹Īéĥ½ä¸į
    -0.24
     SEP
    -0.24
    SEP
    -0.24
    POSITIVE LOGITS
    è¡Ķ
    0.28
    å®ŀ践活åĬ¨
    0.27
    å®ŀè·µä¸Ń
    0.25
    rant
    0.25
    èĨ¨èĥĢ
    0.24
     bub
    0.24
     neglected
    0.24
    oose
    0.24
     curled
    0.24
    inely
    0.23
    Activations Density 0.189%

    No Known Activations