© 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. 5102
    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
    çĵł
    -0.29
    vironment
    -0.27
     Gott
    -0.26
    érc
    -0.26
    agnitude
    -0.25
    gable
    -0.24
     Merr
    -0.24
    aju
    -0.24
    Âł
    -0.23
     rubber
    -0.23
    POSITIVE LOGITS
    Station
    0.27
    _station
    0.26
     Station
    0.26
    ä½Ĩ她
    0.25
     rencontres
    0.25
    èĤ©
    0.25
     intents
    0.25
    åıĺæĢģ
    0.24
    mart
    0.24
     cruis
    0.24
    Activations Density 0.054%

    No Known Activations

    This feature has no known activations.