© 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. 8618
    Prev
    Next
    INDEX
    Explanations

    concepts

    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
    oku
    -0.28
    poons
    -0.25
    zens
    -0.25
    :<?
    -0.25
    订éĺħ
    -0.25
    gens
    -0.25
    copies
    -0.24
    èĪĮå°ĸ
    -0.24
    dur
    -0.24
    licit
    -0.24
    POSITIVE LOGITS
     Intro
    0.28
     overview
    0.28
    overview
    0.28
    olie
    0.28
     over
    0.27
     Overview
    0.27
    Overview
    0.27
    iones
    0.26
     A
    0.25
    æĶ¹èī¯
    0.25
    Activations Density 0.022%

    No Known Activations