© 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. 8171
    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
     upcoming
    -0.27
    apes
    -0.27
     recent
    -0.26
     forthcoming
    -0.26
    ,Z
    -0.24
    isha
    -0.24
    çĹ£
    -0.24
    è¯¥é¡¹çĽ®
    -0.24
    缸è¿ij
    -0.24
    à¹Ħร
    -0.24
    POSITIVE LOGITS
    spiel
    0.33
    yen
    0.29
    大ä¼ļ
    0.27
    åīįèĢħ
    0.26
    UMB
    0.26
    ä¹ľ
    0.26
    æķ£åıij
    0.26
    yers
    0.25
    _CLOCK
    0.25
    sein
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.