© 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. 6810
    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
    lider
    -0.28
    ditor
    -0.27
    访
    -0.25
    æ´
    -0.25
    agi
    -0.25
    ä¿®åħ»
    -0.24
     auditor
    -0.24
    uct
    -0.24
    oha
    -0.24
    å¦Ĥæľī
    -0.23
    POSITIVE LOGITS
    eming
    0.29
    anus
    0.27
     afterward
    0.25
    ä¹ĭåĬĽ
    0.24
     sweating
    0.24
     anthology
    0.24
     anale
    0.24
    çī¯
    0.23
    ä½łèĩªå·±
    0.23
     chac
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.