© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7628
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    icana
    -0.27
     mouth
    -0.25
    quin
    -0.25
    åĺ´å·´
    -0.25
    '-
    -0.24
    .flatMap
    -0.24
    gst
    -0.24
    intern
    -0.24
    èģĶéĤ¦
    -0.24
    annis
    -0.24
    POSITIVE LOGITS
    æĮĩæľĽ
    0.28
    spacer
    0.26
    Filed
    0.26
    éĩı
    0.24
     perfect
    0.24
    igation
    0.24
    è¿ĺæĥ³
    0.24
    ãĤ·ãĤ§
    0.24
    shal
    0.24
    .www
    0.24
    Activations Density 0.001%

    No Known Activations