© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5428
    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
    oha
    -0.27
     minded
    -0.27
     hi
    -0.25
    ilm
    -0.25
     res
    -0.25
     forget
    -0.24
     dav
    -0.24
    oho
    -0.24
    fra
    -0.24
     Bew
    -0.23
    POSITIVE LOGITS
    clipse
    0.28
    æĹłæĥħ
    0.27
     either
    0.27
    éĹ®ä»ĸ
    0.26
    ä¹Łä¸įåı¯èĥ½
    0.26
    ively
    0.26
    icensing
    0.25
    outes
    0.25
    èıĬèĬ±
    0.25
    åĪĹ举
    0.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.