© 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. 4795
    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
    羡
    -0.26
    immer
    -0.25
     Interr
    -0.25
    丽
    -0.25
    èĭ¥æľī
    -0.24
    ipl
    -0.24
     nob
    -0.23
    奸
    -0.23
    éºĹ
    -0.23
    UCH
    -0.23
    POSITIVE LOGITS
    è¯
    0.29
    ä¸įå®Į
    0.27
    /popper
    0.27
    /vnd
    0.27
    adol
    0.26
    lash
    0.25
    pdb
    0.25
    bbing
    0.24
    clipse
    0.23
    åĨħåĪĨæ³Į
    0.23
    Activations Density 1.064%

    No Known Activations

    This feature has no known activations.