© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8850
    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
    forth
    -0.29
    èĥĮæĻ¯
    -0.27
    Raised
    -0.27
    .raise
    -0.27
    ÙĪجب
    -0.26
    lé
    -0.26
    abouts
    -0.26
    _OW
    -0.26
    idad
    -0.25
    è¹Ī
    -0.25
    POSITIVE LOGITS
    éķĤ
    0.28
    ':''
    0.27
    Whole
    0.27
    该æĿij
    0.27
     Frag
    0.26
    å¤Ķ
    0.26
    STS
    0.26
    sti
    0.26
    anol
    0.25
    飧æĢ§
    0.25
    Activations Density 0.155%

    No Known Activations

    This feature has no known activations.