© 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. 8407
    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
     prot
    -0.28
     пÑĢоÑĤ
    -0.26
    egal
    -0.26
    åĤį
    -0.25
     Prot
    -0.24
    åĨį
    -0.24
    æĿ¥è¯´
    -0.24
     protest
    -0.24
    åĬŁ
    -0.23
     versa
    -0.23
    POSITIVE LOGITS
    chine
    0.27
    izzes
    0.27
    agas
    0.26
    pay
    0.26
    ¹Ħ
    0.26
    atically
    0.26
    rait
    0.25
    cı
    0.25
    quÃŃ
    0.24
     Booker
    0.24
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.