© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    Acronyms/Abbreviations

    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
    est
    -0.29
     ties
    -0.27
    esti
    -0.26
     molds
    -0.26
    ests
    -0.26
    .experimental
    -0.26
    isco
    -0.25
    æľ
    -0.25
     scout
    -0.24
    izona
    -0.24
    POSITIVE LOGITS
    igi
    0.27
    oter
    0.27
    åĨł
    0.26
    aptop
    0.25
    TERN
    0.25
    éĢ»
    0.24
     []).
    0.24
    æIJģ
    0.23
    ä»»ä½ķæŶåĢĻ
    0.23
    ARP
    0.23
    Activations Density 0.363%

    No Known Activations