© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 131067
    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
    Negative Logits
     internally
    -0.31
     ninety
    -0.26
    ॥
    -0.25
    bugs
    -0.24
     POLL
    -0.24
    (internal
    -0.24
     EventType
    -0.24
    æħİéĩį
    -0.23
    .Nullable
    -0.23
     clinically
    -0.23
    POSITIVE LOGITS
    弦
    0.27
    ä»Ĺ
    0.26
    asser
    0.26
    ä¸ĸçķĮä¸Ģæµģ
    0.26
    unchecked
    0.24
    ylko
    0.24
    utes
    0.24
    umph
    0.24
     served
    0.23
    unts
    0.23
    Activations Density 0.144%

    No Known Activations

    This feature has no known activations.