© 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. 129027
    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
    çļĦæĥħ
    -0.28
    åĪĨå±Ģ
    -0.27
    lico
    -0.27
     immediate
    -0.27
    agan
    -0.26
    æĢ¥
    -0.25
    heiten
    -0.24
    utan
    -0.24
     forthcoming
    -0.24
    nen
    -0.24
    POSITIVE LOGITS
    ç»ıå¼Ģ
    0.24
    stood
    0.23
     Tough
    0.23
    Ticks
    0.23
     lax
    0.23
     Lyon
    0.23
    beb
    0.22
    __č↵
    0.22
    ous
    0.22
    éĿ
    0.22
    Activations Density 0.177%

    No Known Activations

    This feature has no known activations.