© 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. 111263
    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
     colspan
    -0.30
    ize
    -0.29
    åĨ·éĵ¾çī©æµģ
    -0.27
     understanding
    -0.26
     data
    -0.26
    VML
    -0.25
     mistr
    -0.24
     analysis
    -0.24
    -margin
    -0.24
    DMI
    -0.24
    POSITIVE LOGITS
    iris
    0.34
     pog
    0.27
    ://{
    0.27
    RTC
    0.25
    ounter
    0.25
    atori
    0.25
     Rape
    0.24
     uphol
    0.24
    orer
    0.24
    reso
    0.23
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.