© 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. 111611
    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
    urally
    -0.32
    lane
    -0.27
    iko
    -0.25
    æ´¾
    -0.24
    åıĸ
    -0.24
     обÑĢазом
    -0.24
    å¥ĩ
    -0.24
    creativecommons
    -0.24
    .AnchorStyles
    -0.24
    aleigh
    -0.24
    POSITIVE LOGITS
    IJľç´¢
    0.28
     Brief
    0.27
     Occup
    0.27
    /sources
    0.25
    osg
    0.25
     Occupational
    0.25
     Exterior
    0.25
    äºĨä¸Ģåľº
    0.25
     Arrest
    0.25
    zp
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.