© 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. 8215
    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
    vents
    -0.29
    usz
    -0.28
    visual
    -0.28
    uss
    -0.27
    urre
    -0.26
    è¿Ń
    -0.25
    è§Ĩè§ī
    -0.25
    uÃŁ
    -0.25
    æĪĸå¤ļ
    -0.24
     conceived
    -0.24
    POSITIVE LOGITS
     outnumber
    0.26
    ạp
    0.26
    足迹
    0.26
    ä¸įæĸŃæī©å¤§
    0.26
    èģļéĽĨ
    0.25
    ä¸įæĸŃåĪĽæĸ°
    0.25
    inati
    0.24
    æĬ±ä½ı
    0.24
    åħ´èµ·
    0.24
    otime
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.