© 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. 7853
    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
    aurus
    -0.27
    轨
    -0.26
    æĮ£éĴ±
    -0.26
    TERNAL
    -0.25
    ÑĪки
    -0.24
    -paying
    -0.24
    å°ıå§IJå§IJ
    -0.24
    ROLE
    -0.23
    aea
    -0.23
    edia
    -0.23
    POSITIVE LOGITS
    vection
    0.29
    vas
    0.28
    .Expressions
    0.28
    æľĿ
    0.26
    iration
    0.26
     timer
    0.25
     expression
    0.25
    timer
    0.25
     expressions
    0.25
    çĪ±ä½ł
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.