© 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. 112260
    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
    &oacute
    -0.24
    веÑģÑĤи
    -0.23
    permanent
    -0.23
    轻轻
    -0.23
    mlink
    -0.23
    è¿Ļ两
    -0.23
    еннÑĥÑİ
    -0.23
    ächt
    -0.23
     Lambert
    -0.23
    ercul
    -0.23
    POSITIVE LOGITS
    ogue
    0.28
    -clock
    0.23
     massages
    0.23
    alers
    0.23
    æį»
    0.22
    ickness
    0.22
    å·®çĤ¹
    0.22
     snacks
    0.22
     autofocus
    0.22
    椿
    0.21
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.