© 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. 130487
    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
    chor
    -0.27
     sp
    -0.27
    vas
    -0.27
     evacuation
    -0.25
     reached
    -0.25
     mùa
    -0.25
    _dependency
    -0.24
    ocation
    -0.24
    sp
    -0.24
     interaction
    -0.24
    POSITIVE LOGITS
    hread
    0.30
     JOB
    0.25
    ä»»åĬ¡
    0.24
    ä¹°åįķ
    0.23
    >Z
    0.23
    为æѤ
    0.23
    çİĽä¸½
    0.23
    htag
    0.23
    \xd
    0.23
    Drupal
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.