© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7382
    Prev
    Next
    INDEX
    Explanations

    Unusual text

    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
    ologies
    -0.26
     cycle
    -0.25
    æĦıè¯Ĩ
    -0.24
    itä
    -0.24
    ť
    -0.24
    å«Į
    -0.24
    æĪijæīį
    -0.23
    æĢİä¹Īåģļ
    -0.23
    åºĶ对
    -0.23
    ection
    -0.23
    POSITIVE LOGITS
    åIJı
    0.28
    .addEdge
    0.26
    สà¸ĸ
    0.24
    ALLY
    0.24
    æĤį
    0.24
    (ord
    0.24
     IMPORTANT
    0.24
    quiv
    0.24
    cat
    0.23
    /wiki
    0.23
    Activations Density 0.002%

    No Known Activations