© 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. 20-TRANSCODER-HP
    7. 108018
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antity
    -0.27
    å°½éĩı
    -0.26
     jeste
    -0.26
    éķĩ
    -0.25
    ener
    -0.25
    ows
    -0.25
     wij
    -0.24
    赶快
    -0.24
    ka
    -0.24
    è´¶
    -0.23
    POSITIVE LOGITS
    æĬ±
    0.28
    æľīçļĦçݩ家
    0.26
    è¹Ī
    0.26
     tôn
    0.24
    (Fl
    0.24
     offseason
    0.23
    pag
    0.23
    FormatException
    0.23
    (Build
    0.23
    าà¸ĩ
    0.23
    Activations Density 3.033%

    No Known Activations

    This feature has no known activations.