© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    location

    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
    豫
    -0.26
    ignet
    -0.25
    BED
    -0.25
     beds
    -0.25
    åºĬä½į
    -0.24
    disposing
    -0.24
     receipt
    -0.23
     subsection
    -0.23
     Beds
    -0.23
    å¿ĥèĦıçĹħ
    -0.23
    POSITIVE LOGITS
    alus
    0.28
    stand
    0.28
    shoot
    0.26
    college
    0.24
    便
    0.24
    fo
    0.23
    allas
    0.23
    è¯ļ
    0.23
     meas
    0.23
    cone
    0.23
    Activations Density 0.166%

    No Known Activations