© 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. 87165
    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
     Nielsen
    -0.30
    arking
    -0.27
     Nexus
    -0.27
     Gold
    -0.26
     Pis
    -0.25
    enheim
    -0.25
    geh
    -0.25
    ulative
    -0.24
    cum
    -0.24
     layer
    -0.24
    POSITIVE LOGITS
     ')[
    0.28
    主è¦ģåĨħ容
    0.27
    åŃĺåľ¨
    0.27
    ç¨ĭ
    0.25
    æĭĶ
    0.25
    è¦ģåģļ
    0.24
    åħ·æľīä¸Ģå®ļ
    0.24
    åıįçľģ
    0.24
    åĬ¡
    0.24
    antis
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.