© 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. 9454
    Prev
    Next
    INDEX
    Explanations

    Parentheses and hyphens

    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
    çľģæķĻèĤ²
    -0.30
    renc
    -0.27
    .kr
    -0.26
    ictions
    -0.25
    åºĬ
    -0.25
    ently
    -0.25
     machine
    -0.25
    çŁŃæľŁ
    -0.24
     imp
    -0.24
     short
    -0.24
    POSITIVE LOGITS
    elight
    0.30
    èĩªå¦Ĥ
    0.25
    æĶ¯æĮģ
    0.25
    parator
    0.25
    âĹĪ
    0.25
    ERE
    0.24
    errick
    0.24
    éķĵ
    0.24
    GRES
    0.23
    å°±è¿Ļæł·
    0.23
    Activations Density 0.012%

    No Known Activations