© 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. 4693
    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
    åįķ车
    -0.31
    :host
    -0.29
     unc
    -0.27
    xc
    -0.26
    olio
    -0.26
    éĩıåĮĸ
    -0.25
    YNAM
    -0.25
    heit
    -0.25
    ball
    -0.24
    CBD
    -0.23
    POSITIVE LOGITS
    asu
    0.28
    没åħ³ç³»
    0.27
     Walters
    0.27
    ingroup
    0.26
    å¨ĵ
    0.26
     intermedi
    0.25
    뮤
    0.24
    è®·
    0.24
    otel
    0.24
    appa
    0.24
    Activations Density 1.241%

    No Known Activations

    This feature has no known activations.