© 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. 107358
    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
     spent
    -0.29
    å°Ķ
    -0.27
    ku
    -0.25
    ys
    -0.25
     spending
    -0.25
    åī²
    -0.25
    kat
    -0.25
    çĬĴ
    -0.25
    çĮ®
    -0.25
    çĻ¾
    -0.25
    POSITIVE LOGITS
    å¾Ĺå¾Ī好
    0.29
    åħ¨æĹ¥åĪ¶
    0.28
     flex
    0.26
    ä¸įå¼Ģ
    0.25
     miejsc
    0.25
    wayne
    0.25
    æŃ»è§Ĵ
    0.25
    ãĤ¬ãĤ¤ãĥī
    0.25
     hoses
    0.25
    пÑĢÑı
    0.24
    Activations Density 11.862%

    No Known Activations

    This feature has no known activations.