© 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. 6814
    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
    ality
    -0.29
    åIJĪ
    -0.27
    UDO
    -0.27
     GDP
    -0.25
    åĬłåĽº
    -0.25
    åĢĴ
    -0.24
    udo
    -0.24
    æµħ
    -0.24
    è§Ħ模
    -0.23
    $k
    -0.23
    POSITIVE LOGITS
    ytt
    0.28
     unwind
    0.27
    infeld
    0.26
    wer
    0.26
    wers
    0.25
    isseur
    0.25
    çļĦçIJĨæĥ³
    0.25
     référence
    0.24
    feld
    0.24
     masturb
    0.24
    Activations Density 0.053%

    No Known Activations

    This feature has no known activations.