© 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. 108343
    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
     financed
    -0.31
    æĸĭ
    -0.28
    kses
    -0.27
    æĭIJ
    -0.27
    {}
    -0.27
     paced
    -0.26
    nage
    -0.25
     {_
    -0.25
    åħ¬ç½ijå®īå¤ĩ
    -0.24
    çķĢ
    -0.24
    POSITIVE LOGITS
    ells
    0.27
     OPT
    0.26
    OPT
    0.26
    ä¼ĺ
    0.24
     rankings
    0.24
     answers
    0.23
     suggestion
    0.23
    rial
    0.23
     lower
    0.23
     bla
    0.23
    Activations Density 0.449%

    No Known Activations

    This feature has no known activations.