© 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. 4768
    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
    æ³ķ
    -0.26
    lan
    -0.26
    Attr
    -0.26
    _LONG
    -0.25
    feit
    -0.25
    <long
    -0.24
    PTY
    -0.23
    éĢĨ
    -0.23
    æ°ı
    -0.23
    ä¹Łè®¸æĺ¯
    -0.23
    POSITIVE LOGITS
    æĤ¬æµ®
    0.37
    æĤ¬
    0.28
     matter
    0.25
    éĴĹ
    0.24
    åħ¬åħ±èµĦæºIJ
    0.24
     whe
    0.24
    ewire
    0.24
    èĢ³è¾¹
    0.24
    æĥ¯
    0.23
     emerges
    0.23
    Activations Density 0.160%

    No Known Activations

    This feature has no known activations.