© 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. 5148
    Prev
    Next
    INDEX
    Explanations

    if

    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
    .cgi
    -0.29
    quals
    -0.29
    %H
    -0.28
    æĦıåĽ¾
    -0.28
    benh
    -0.26
    fid
    -0.26
     Cad
    -0.25
    engan
    -0.25
     addAction
    -0.25
    .WebControls
    -0.25
    POSITIVE LOGITS
    è±ģ
    0.29
     weaker
    0.25
    çݯèĬĤ
    0.25
    æĭħä¿Ŀ
    0.24
    èĥĮ
    0.24
    æ¯Ĵ
    0.24
    hood
    0.24
     vụ
    0.24
     exotic
    0.24
    æĢĢéĩĮ
    0.24
    Activations Density 0.319%

    No Known Activations