© 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. 18-TRANSCODER-HP
    7. 89987
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stead
    -0.27
     surre
    -0.25
    UF
    -0.24
    Sign
    -0.24
    ï¼ģ”
    -0.23
    ิà¸ĩ
    -0.23
    UEL
    -0.23
    çŁ¥ãĤīãģªãģĦ
    -0.23
    _tD
    -0.23
    uel
    -0.23
    POSITIVE LOGITS
     Palestine
    0.26
    kit
    0.25
    nable
    0.25
    ãĥıãĥ³
    0.24
     notch
    0.24
    arlo
    0.24
    erna
    0.24
    arna
    0.24
    å°¼åħĭ
    0.23
     Democr
    0.23
    Activations Density 13.732%

    No Known Activations

    This feature has no known activations.