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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4721
    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
    æĦıè§ģåıįé¦Ī
    -0.28
    eka
    -0.28
    èķī
    -0.26
    æľ¬ç½ij
    -0.26
    å¿ĺ
    -0.25
    帰ãĤĬ
    -0.25
    è½®
    -0.25
    igte
    -0.25
    oria
    -0.25
    å¿ĺè®°äºĨ
    -0.25
    POSITIVE LOGITS
    æĶ¶åıĸ
    0.27
    scopes
    0.26
     positive
    0.25
     exc
    0.25
    pic
    0.25
    _scope
    0.24
    positive
    0.24
    mers
    0.24
    itest
    0.23
     tract
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.