© 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. 7567
    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
    åŃIJéĩĮ
    -0.29
     prez
    -0.25
    éĩįè¦ģ
    -0.25
    Important
    -0.25
     minist
    -0.24
    å¼±åĬ¿
    -0.23
     academics
    -0.23
     Usage
    -0.23
    [model
    -0.23
     nas
    -0.23
    POSITIVE LOGITS
    åºĬ
    0.30
    èĥ¶
    0.29
     gel
    0.29
     rubber
    0.28
    åĨį
    0.27
    0.26
    å¹²
    0.26
    vio
    0.25
    eos
    0.25
     Ard
    0.24
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.