© 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. 9327
    Prev
    Next
    INDEX
    Explanations

    draw

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rames
    -0.29
    å·²ä¹ħçļĦ
    -0.27
    deo
    -0.27
    æĪijåıªæĺ¯
    -0.26
    Frames
    -0.25
     quo
    -0.25
    [--
    -0.23
    们çļĦ
    -0.23
    ="--
    -0.23
     livest
    -0.22
    POSITIVE LOGITS
     attention
    0.30
    ler
    0.27
    ings
    0.26
    éĺħ读åħ¨æĸĩ
    0.24
    out
    0.24
     from
    0.24
    books
    0.24
    -room
    0.24
    endance
    0.24
    ãĤ¹ãĥĿ
    0.23
    Activations Density 3.543%

    No Known Activations