© 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. 8456
    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
    ä¿Ŀå®Ī
    -0.25
    arness
    -0.24
    باØŃ
    -0.24
    @Spring
    -0.24
    罩
    -0.24
    æĬ±
    -0.24
    ahr
    -0.24
    _ctxt
    -0.24
    minster
    -0.24
    erald
    -0.24
    POSITIVE LOGITS
     eof
    0.26
    antages
    0.25
    hea
    0.25
     itemprop
    0.25
     Pet
    0.24
     pesso
    0.24
    èݪ
    0.24
    OOM
    0.24
    agi
    0.24
    èĩªçIJĨ
    0.23
    Activations Density 0.245%

    No Known Activations

    This feature has no known activations.