© 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. 6226
    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
    _generated
    -0.29
    ixture
    -0.27
     fisse
    -0.26
    combination
    -0.26
    unner
    -0.25
    éĶĭ
    -0.25
     suitcase
    -0.25
    ATRIX
    -0.24
    hunt
    -0.23
     looph
    -0.23
    POSITIVE LOGITS
    è¿ľç¦»
    0.27
    NR
    0.26
    isons
    0.26
    sto
    0.25
    CR
    0.25
    volt
    0.25
    avar
    0.24
    æĢ¨
    0.24
    eterangan
    0.24
    ä¸ĩ个
    0.24
    Activations Density 0.049%

    No Known Activations

    This feature has no known activations.