© 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. 87679
    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
     compare
    -0.39
    compare
    -0.33
     Compare
    -0.32
    .compare
    -0.29
     compares
    -0.29
    Compare
    -0.28
    ή
    -0.27
     comparing
    -0.26
    .Compare
    -0.26
    类产åĵģ
    -0.26
    POSITIVE LOGITS
    agos
    0.27
     brief
    0.27
    	component
    0.26
    earch
    0.25
    [Any
    0.25
    vided
    0.24
    reating
    0.24
    orning
    0.24
     friendly
    0.24
    ear
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.