© 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. 7677
    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
     appealing
    -0.29
    åħħå®ŀ
    -0.27
    åıijæĮ¥ä½ľçĶ¨
    -0.26
    ç¢ī
    -0.25
    äºĭæķħåıijçĶŁ
    -0.24
     Opens
    -0.24
    _bullet
    -0.24
     dispar
    -0.24
     opener
    -0.24
    åĬ¨äºº
    -0.23
    POSITIVE LOGITS
    å¤ĩ
    0.27
    iset
    0.27
     rational
    0.26
    èµĦ产管çIJĨ
    0.26
    ej
    0.25
    ìłķ
    0.25
    -example
    0.25
    hdl
    0.25
    .AddComponent
    0.25
    azard
    0.25
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.