© 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. 6482
    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
     Dud
    -0.29
     least
    -0.27
     Least
    -0.26
    íķŃ
    -0.25
     schl
    -0.25
    æĺ§
    -0.25
    olson
    -0.25
     Highlands
    -0.25
    arine
    -0.24
    头èĦij
    -0.24
    POSITIVE LOGITS
    loy
    0.30
    powers
    0.25
    设计çIJĨ念
    0.25
    .SEVER
    0.24
    eresa
    0.24
    è¿ŀè½½
    0.24
    ä¸Ģ个éĹ®é¢ĺ
    0.24
    æĴ¼
    0.24
    cuts
    0.24
    LOY
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.