© 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. 8897
    Prev
    Next
    INDEX
    Explanations

    difference

    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
    oso
    -0.25
    ÙĪØ«
    -0.25
    èĩªè§ī
    -0.25
     conscient
    -0.25
     redund
    -0.24
    _documents
    -0.24
    ument
    -0.24
    [W
    -0.24
    羡
    -0.23
    <Tag
    -0.23
    POSITIVE LOGITS
     differ
    0.36
     differs
    0.36
     different
    0.32
    ä¸įåIJĮçļĦ
    0.32
     differently
    0.32
     compared
    0.32
     changing
    0.32
     dynamics
    0.31
    æĪª
    0.31
     changed
    0.30
    Activations Density 0.518%

    No Known Activations