© 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. 5193
    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
     loft
    -0.29
    èĮĥæĸĩ
    -0.25
    é¾Ĥ
    -0.24
    Ñĭми
    -0.24
    ä¸Ģç«Ļ
    -0.24
    Mui
    -0.24
    ä½įç½®
    -0.23
    orch
    -0.23
    ousel
    -0.23
    orrect
    -0.23
    POSITIVE LOGITS
    REET
    0.28
    éĻ¢éĻ¢å£«
    0.24
     posted
    0.24
    erno
    0.24
     SUBSTITUTE
    0.23
    utral
    0.23
    æĹĦ
    0.23
    eties
    0.23
    roupe
    0.23
     amet
    0.23
    Activations Density 0.183%

    No Known Activations

    This feature has no known activations.