© 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. 141088
    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
    ëŀ¬
    -0.29
    è¿ĻéĩĮçļĦ
    -0.29
    leigh
    -0.27
    tti
    -0.25
    woord
    -0.25
    ä¸įè§ģäºĨ
    -0.24
    综
    -0.24
    iese
    -0.24
    utors
    -0.24
    à¹Ĥà¸Ĺษ
    -0.24
    POSITIVE LOGITS
    escal
    0.28
    thur
    0.26
     Performance
    0.25
    çİĩ
    0.25
    å°ļæľª
    0.24
     Occup
    0.24
     Mobility
    0.23
    Ins
    0.23
     occup
    0.23
    emu
    0.23
    Activations Density 40.629%

    No Known Activations

    This feature has no known activations.