© 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. 5887
    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
    éĴ¿
    -0.27
    обÑīа
    -0.26
    arkin
    -0.26
     bench
    -0.26
    allen
    -0.26
    onen
    -0.25
    ertainty
    -0.24
    ucht
    -0.24
    æ·³
    -0.24
     Expected
    -0.24
    POSITIVE LOGITS
    èĪŀ
    0.27
    åĬ¿
    0.25
    æ¡£
    0.25
    æ´º
    0.25
    cpy
    0.25
    implicitly
    0.24
    ixmap
    0.24
     Nest
    0.24
    uffy
    0.24
    硬åĮĸ
    0.24
    Activations Density 0.043%

    No Known Activations

    This feature has no known activations.