© 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. 9177
    Prev
    Next
    INDEX
    Explanations

    Common English articles

    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
    秫
    -0.28
     kem
    -0.26
    bilt
    -0.24
     dcc
    -0.24
    enticator
    -0.24
     DNC
    -0.24
    timeofday
    -0.23
    åİŁæĸĩ
    -0.23
    spiracy
    -0.23
    ç½Ķ
    -0.23
    POSITIVE LOGITS
     publié
    0.29
    rita
    0.28
    usu
    0.28
    è¿«
    0.27
    é¼ĵ
    0.27
    åĬ¿
    0.27
    rys
    0.26
     determination
    0.26
    undle
    0.26
     acab
    0.25
    Activations Density 0.023%

    No Known Activations