© 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. 7723
    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
    ington
    -0.27
    æ²ī
    -0.26
    Ba
    -0.26
     Ba
    -0.25
    sequence
    -0.25
    DNA
    -0.25
    ÂŃtion
    -0.24
     eid
    -0.24
    æŃ£éĿ¢
    -0.24
    è¶ħè¿ĩ
    -0.24
    POSITIVE LOGITS
    Stroke
    0.23
     ContentView
    0.23
    boro
    0.23
     transient
    0.23
    iff
    0.23
     électrique
    0.22
    æ¢
    0.22
    享çĶ¨
    0.22
    è¿ijæĹ¥
    0.22
    æį©
    0.22
    Activations Density 0.857%

    No Known Activations

    This feature has no known activations.