© 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. 111900
    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
    /mit
    -0.28
    /API
    -0.28
    orough
    -0.26
    æŀ§
    -0.26
    surname
    -0.26
     Memories
    -0.25
    GroupName
    -0.24
    å¼Ģæ°´
    -0.24
     dataTable
    -0.24
     seats
    -0.24
    POSITIVE LOGITS
     be
    0.27
     virtual
    0.27
    èĻļæĭŁ
    0.26
     falls
    0.26
    wis
    0.26
    èIJ½
    0.26
     Block
    0.25
     block
    0.25
     aging
    0.25
    èĻ½
    0.25
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.