© 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. 128979
    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
    isNaN
    -0.27
    efeller
    -0.26
    åĪºæ¿Ģ
    -0.26
    .getRuntime
    -0.26
    ategorized
    -0.25
    aaS
    -0.25
    -parse
    -0.25
    ?,?,?,?,
    -0.25
    çĶŁ
    -0.24
    ç»ĵæŀľ
    -0.24
    POSITIVE LOGITS
    æĿIJ
    0.34
     att
    0.27
    ola
    0.27
     supervise
    0.26
    ogo
    0.26
    åĢĻ
    0.25
    éĻį
    0.24
    ¤
    0.24
    (bundle
    0.24
    bundle
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.