© 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. 8948
    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
    ikon
    -0.28
    ÙĨا
    -0.26
    èĸª
    -0.24
    utor
    -0.23
    -national
    -0.23
    幡
    -0.23
    ONSE
    -0.23
    åĪĨæµģ
    -0.23
    .watch
    -0.23
    éĹª
    -0.23
    POSITIVE LOGITS
    ÑĮ
    0.27
    PELL
    0.26
    uby
    0.25
    QUAL
    0.25
    æŁ¬
    0.25
    Äı
    0.25
    ä»ĸä»¬åľ¨
    0.25
    ocular
    0.24
    äs
    0.24
    鹦
    0.24
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.