© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6982
    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
     ev
    -0.26
     refr
    -0.25
    :item
    -0.24
    åĬŀ好
    -0.23
    Reply
    -0.23
    æ¶ķ
    -0.23
     Animator
    -0.23
    moid
    -0.23
     BaseEntity
    -0.23
    Statics
    -0.22
    POSITIVE LOGITS
    åįij
    0.30
    illac
    0.27
    uge
    0.26
    kers
    0.26
    ä¹ĭåīį
    0.26
    ILL
    0.25
     surprises
    0.25
    Low
    0.25
    åŃļ
    0.25
     prior
    0.25
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.