© 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. 8005
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical data

    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
    .mx
    -0.28
    ä¸Ģè§Ĵ
    -0.27
    èĽĦ
    -0.26
    unan
    -0.26
    Unnamed
    -0.25
    dings
    -0.25
    è¿Ļæĺ¯ä¸Ģç§į
    -0.25
    ç¢ĩ
    -0.25
    baum
    -0.25
    ä¸īæĺŁ
    -0.25
    POSITIVE LOGITS
    åĴĮ
    0.36
     and
    0.35
     or
    0.31
     mol
    0.28
    +",
    0.27
     åĴĮ
    0.27
     и
    0.26
    ãĢģ
    0.26
    0.26
    iv
    0.25
    Activations Density 0.074%

    No Known Activations