© 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. 90013
    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
     MISS
    -0.29
    ariat
    -0.27
    ä¸Ńåħ³
    -0.26
    å¼¥
    -0.26
    ä¸Ńéĵģ
    -0.25
    erez
    -0.25
    .gs
    -0.24
    æİ£
    -0.24
    quis
    -0.24
    大桥
    -0.24
    POSITIVE LOGITS
    ä½Ĩä¹Ł
    0.30
    asing
    0.29
    enz
    0.28
    ç´ł
    0.28
     also
    0.28
    åĽ½
    0.26
    also
    0.26
    igy
    0.26
     affine
    0.26
     unr
    0.26
    Activations Density 0.392%

    No Known Activations

    This feature has no known activations.