© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8545
    Prev
    Next
    INDEX
    Explanations

    more/greater/faster/higher/stronger

    np_max-act · gemini-2.0-flash
    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
    oard
    -0.29
     development
    -0.28
    YW
    -0.27
    Appe
    -0.27
    Nam
    -0.27
    -development
    -0.27
    DON
    -0.26
    ä¹ŁéľĢè¦ģ
    -0.26
    Ease
    -0.26
    OWN
    -0.25
    POSITIVE LOGITS
    achel
    0.30
    ellig
    0.27
    ogl
    0.24
    åĨ¶éĩij
    0.24
    åĬ£
    0.24
     ResultSet
    0.24
    lesc
    0.24
    öff
    0.24
     DependencyProperty
    0.23
    gger
    0.23
    Activations Density 0.015%

    No Known Activations