© 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. 6293
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    oug
    -0.10
    createClass
    -0.10
    xED
    -0.10
    coh
    -0.10
    uges
    -0.10
    .changed
    -0.10
    åı«æĪij
    -0.09
    enstein
    -0.09
    umed
    -0.09
     har
    -0.09
    POSITIVE LOGITS
    иÑĩно
    0.10
    енÑĤа
    0.10
    »
    0.10
    ãĤĦãĤĬ
    0.10
    éģĹçķĻ
    0.09
     Concept
    0.09
     ÐĴлад
    0.09
     ÐĿово
    0.09
     Fact
    0.09
     People
    0.09
    Activations Density 0.150%

    No Known Activations