© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5172
    Prev
    Next
    INDEX
    Explanations

    measurement and analysis techniques

    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
    æĪIJå°±
    -0.28
    otics
    -0.28
    anut
    -0.26
    >{!!
    -0.26
    comings
    -0.25
    åķĬ
    -0.25
    del
    -0.24
    etime
    -0.24
    dea
    -0.24
    road
    -0.24
    POSITIVE LOGITS
    FORCE
    0.26
    goog
    0.25
    theses
    0.24
    ï¬ĥ
    0.23
    columns
    0.23
    ILog
    0.23
    éĵĪ
    0.23
     IMPLIED
    0.23
    Porn
    0.23
     geme
    0.23
    Activations Density 0.815%

    No Known Activations