© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    generic english sentences

    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
    éĤ£ä¹Īå¤ļ
    -0.28
    fäh
    -0.27
    溶
    -0.26
    被æīĵ
    -0.26
     sane
    -0.25
    æĭĽçīĮ
    -0.25
     TOUCH
    -0.25
     Humanity
    -0.24
    éĢļåijĬ
    -0.24
     warp
    -0.24
    POSITIVE LOGITS
     reserve
    0.28
    éªł
    0.25
     super
    0.24
    ial
    0.23
    ATUS
    0.23
    hel
    0.23
     reserves
    0.23
    ç¼İ
    0.23
    å¹½é»ĺ
    0.23
    å°ij女
    0.23
    Activations Density 0.236%

    No Known Activations