© 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. 141707
    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
    usta
    -0.28
    unfinished
    -0.27
    éķ¶åµĮ
    -0.26
    end
    -0.26
    #ac
    -0.25
    erb
    -0.25
    acerb
    -0.24
    奢ä¾Ī
    -0.23
    orestation
    -0.23
    endance
    -0.23
    POSITIVE LOGITS
    Gran
    0.25
    å¼Ł
    0.23
     Irr
    0.23
     Yun
    0.23
    âĢŀ
    0.23
    retain
    0.22
    irts
    0.22
    æĸ¯é¡¿
    0.22
    åĩłåĪĨéĴŁ
    0.22
     sus
    0.22
    Activations Density 1.988%

    No Known Activations

    This feature has no known activations.