© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6603
    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
     EOS
    -0.28
    PosY
    -0.27
    posé
    -0.27
     Pos
    -0.26
    -pos
    -0.26
    PosX
    -0.24
    çĽĺ
    -0.24
     POS
    -0.24
    pell
    -0.24
    pos
    -0.24
    POSITIVE LOGITS
    使人
    0.28
    nam
    0.27
    人å¿ĥ
    0.26
    çļĦ人æĿ¥è¯´
    0.25
    hec
    0.25
    çIJ®
    0.24
    ç¾ŀ
    0.23
    éĺĸ
    0.23
    äºĨä¸Ģä¸ĭ
    0.23
    Bid
    0.23
    Activations Density 0.064%

    No Known Activations

    This feature has no known activations.