© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8211
    Prev
    Next
    INDEX
    Explanations

    Highlighting/marking text

    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
    æĹłéľĢ
    -0.27
     witnessed
    -0.27
     contrasting
    -0.26
     Contrast
    -0.24
    []{
    -0.24
     bicy
    -0.24
    tie
    -0.24
     witness
    -0.24
    URING
    -0.24
    isto
    -0.23
    POSITIVE LOGITS
     certain
    0.29
    -lined
    0.25
    erview
    0.25
    iente
    0.25
    -del
    0.24
    ä¹łæĥ¯äºĨ
    0.24
    ıkl
    0.24
    pleted
    0.24
    æŁIJäºĽ
    0.24
     Certain
    0.24
    Activations Density 0.015%

    No Known Activations