© 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. 8698
    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
    icha
    -0.30
    åIJĪèµĦ
    -0.29
    ITHER
    -0.26
    -basket
    -0.26
    æĪı
    -0.25
    placeholders
    -0.25
    lessly
    -0.24
     IMDb
    -0.24
    pNet
    -0.24
    ä¼ĹæīĢ
    -0.24
    POSITIVE LOGITS
    缴
    0.27
    oo
    0.26
     exam
    0.24
    ubre
    0.24
    asm
    0.24
     pressing
    0.24
    äºĨ解
    0.24
    è¿ĺåİŁ
    0.23
    Answer
    0.23
     polys
    0.23
    Activations Density 1.434%

    No Known Activations

    This feature has no known activations.