© 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. 4744
    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
    PTY
    -0.30
    æī«ä¸Ģæī«
    -0.29
    æĮĩçĶ²
    -0.28
    ½æķ°
    -0.25
    annah
    -0.25
    ole
    -0.24
     remodeling
    -0.24
     masse
    -0.24
    angling
    -0.24
    èĮĿ
    -0.24
    POSITIVE LOGITS
    unit
    0.28
    plied
    0.27
     inherited
    0.25
    specs
    0.24
    mut
    0.24
    illa
    0.24
    pled
    0.24
    ffer
    0.24
    thing
    0.24
    容
    0.24
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.