© 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. 6190
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Frames
    -0.29
    >}
    -0.28
    -wow
    -0.26
    خت
    -0.24
     dll
    -0.24
    vant
    -0.24
    gre
    -0.24
     Diagnostic
    -0.23
    饱åĴĮ
    -0.23
    Frames
    -0.23
    POSITIVE LOGITS
    .NewReader
    0.25
    lh
    0.25
    à¹Ģà¸Ĺ
    0.25
    TEE
    0.25
    ees
    0.24
     nothing
    0.24
    è¯ķçĤ¹å·¥ä½ľ
    0.24
    otto
    0.24
     hypo
    0.24
    ée
    0.24
    Activations Density 0.283%

    No Known Activations

    This feature has no known activations.