© 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. 112833
    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
     high
    -0.26
     increased
    -0.25
     fopen
    -0.25
    erez
    -0.25
     pesso
    -0.24
    çĤ¼
    -0.24
     government
    -0.24
    _
    -0.24
    owa
    -0.24
    æĶ¿åºľ
    -0.24
    POSITIVE LOGITS
    iid
    0.28
    sse
    0.28
    ommen
    0.26
    åķĨ家
    0.25
    txn
    0.25
    aks
    0.24
    xAD
    0.24
    ắp
    0.24
    imary
    0.24
    .TO
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.