© 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. 7254
    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
    aved
    -0.28
    æŀ¶
    -0.26
    >--
    -0.25
     pronto
    -0.24
     kes
    -0.24
    åݨ
    -0.24
     ASAP
    -0.24
    丼
    -0.24
     crib
    -0.23
    PM
    -0.23
    POSITIVE LOGITS
    strand
    0.29
    ä¸į说
    0.28
    decl
    0.27
    ruptcy
    0.26
    Decl
    0.25
    ắm
    0.25
     DECL
    0.24
    åħī彩
    0.24
    strup
    0.24
     ||č↵
    0.23
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.