© 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. 22-TRANSCODER-HP
    7. 87965
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ags
    -0.27
    UAL
    -0.26
    aged
    -0.25
    than
    -0.24
     transc
    -0.24
    agar
    -0.24
     conven
    -0.23
    .shtml
    -0.23
    xAB
    -0.23
    //*
    -0.23
    POSITIVE LOGITS
    è¿ĺéľĢè¦ģ
    0.51
     also
    0.49
    Also
    0.48
     Also
    0.48
    ä¹ŁéľĢè¦ģ
    0.47
     Additionally
    0.44
    Additionally
    0.43
    è¿ĺè¦ģ
    0.43
    ä¹Łè¦ģ
    0.43
    åı¦å¤ĸ
    0.42
    Activations Density 0.000%

    No Known Activations