© 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. 5286
    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
    w
    -0.27
    HER
    -0.26
    going
    -0.26
    herit
    -0.26
    ocator
    -0.25
    unque
    -0.25
     e
    -0.24
     l
    -0.24
    ,e
    -0.24
     ret
    -0.24
    POSITIVE LOGITS
    odont
    0.28
    .bp
    0.27
    .flash
    0.26
    baum
    0.26
    аÑĢÑĤ
    0.25
     peas
    0.24
    ectar
    0.24
    =cut
    0.24
     {};č↵
    0.24
    ASIC
    0.24
    Activations Density 0.256%

    No Known Activations

    This feature has no known activations.